{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/cars196","name":"CARS196","full_name":null,"description_markdown":"CARS196  is composed of 16,185 car images of 196 classes.","description_withheld":null,"homepage":"https://ai.stanford.edu/~jkrause/cars/car_dataset.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Image Retrieval","url":"/task/image-retrieval","datasets_with_task":"/datasets/task/image-retrieval"},{"name":"Image Clustering","url":"/task/image-clustering","datasets_with_task":"/datasets/task/image-clustering"},{"name":"Metric Learning","url":"/task/metric-learning","datasets_with_task":"/datasets/task/metric-learning"}],"languages":[],"variants":["CARS196"],"data_loaders":[],"num_papers_in_archive":43,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/metric-learning-on-cars196","task":"Metric Learning","dataset_variant":"CARS196","rows":36,"metrics":["R@1"],"first_row_in_archive_order":{"model":"Unicom+ViT-L@336px","paper":"/paper/unicom-universal-and-compact-representation","metrics":{"R@1":"98.2"},"code_links":[{"title":"OML-Team/open-metric-learning","url":"https://github.com/OML-Team/open-metric-learning"},{"title":"deepglint/unicom","url":"https://github.com/deepglint/unicom"},{"title":"RocketFlash/easy_metric_learning","url":"https://github.com/RocketFlash/easy_metric_learning/tree/master/tools"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-retrieval-on-cars196","task":"Image Retrieval","dataset_variant":"CARS196","rows":8,"metrics":["R@1","R@8"],"first_row_in_archive_order":{"model":"CGD (MG/SG)","paper":"/paper/combination-of-multiple-global-descriptors","metrics":{"R@1":"94.8"},"code_links":[{"title":"naver/cgd","url":"https://github.com/naver/cgd"},{"title":"leftthomas/CGD","url":"https://github.com/leftthomas/CGD"},{"title":"clovaai/embedding-expansion","url":"https://github.com/clovaai/embedding-expansion"},{"title":"flyingsheepbin/pet-biometrics","url":"https://github.com/flyingsheepbin/pet-biometrics"},{"title":"puneesh00/loop","url":"https://github.com/puneesh00/loop"},{"title":"PuchatekwSzortach/combination_of_multiple_global_descriptors_for_image_retrieval","url":"https://github.com/PuchatekwSzortach/combination_of_multiple_global_descriptors_for_image_retrieval"},{"title":"Samjoel3101/Self-Supervised-Learning-fastai2","url":"https://github.com/Samjoel3101/Self-Supervised-Learning-fastai2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-classification-on-cars196","task":"Image Classification","dataset_variant":"CARS196","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"µ2Net+ (ViT-L/16)","paper":"/paper/a-continual-development-methodology-for-large","metrics":{"Accuracy":"87.18"},"code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/muNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-clustering-on-cars196","task":"Image Clustering","dataset_variant":"CARS196","rows":1,"metrics":["NMI"],"first_row_in_archive_order":{"model":"MES-Loss","paper":"/paper/mes-loss-mutually-equidistant-separation","metrics":{"NMI":"74.82"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":36,"of":36,"counts":{"papers_with_a_benchmark_row":36,"with_a_code_link":30,"where_syntology_ran_a_sample":22,"not_listed_spam_title":0,"listed":36,"listed_where_code_ran":22,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":19,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":19,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/learning-semantic-proxies-from-visual-prompts","slug":"learning-semantic-proxies-from-visual-prompts","title":"Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning","date":"2024-02-04","arxiv_id":"2402.02340","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["noahsark/parameterefficient-dml"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-semantic-proxies-from-visual-prompts#ran","syntology_url":"https://syntology.ai/paper/2402.02340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02340"}}}},{"paper":"/paper/center-contrastive-loss-for-metric-learning","slug":"center-contrastive-loss-for-metric-learning","title":"Center Contrastive Loss for Metric Learning","date":"2023-08-01","arxiv_id":"2308.00458","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mes-loss-mutually-equidistant-separation","slug":"mes-loss-mutually-equidistant-separation","title":"MES-Loss: Mutually equidistant separation metric learning loss function","date":"2023-08-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/unicom-universal-and-compact-representation","slug":"unicom-universal-and-compact-representation","title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","date":"2023-04-12","arxiv_id":"2304.05884","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":6,"official":{"repos":["deepglint/unicom"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unicom-universal-and-compact-representation#ran","syntology_url":"https://syntology.ai/paper/2304.05884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05884"}}}},{"paper":"/paper/a-continual-development-methodology-for-large","slug":"a-continual-development-methodology-for-large","title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","date":"2022-09-15","arxiv_id":"2209.07326","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/das-densely-anchored-sampling-for-deep-metric","slug":"das-densely-anchored-sampling-for-deep-metric","title":"DAS: Densely-Anchored Sampling for Deep Metric Learning","date":"2022-07-30","arxiv_id":"2208.00119","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["lizhaoliu-Lec/DAS"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/das-densely-anchored-sampling-for-deep-metric#ran","syntology_url":"https://syntology.ai/paper/2208.00119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.00119"}}}},{"paper":"/paper/attributable-visual-similarity-learning","slug":"attributable-visual-similarity-learning","title":"Attributable Visual Similarity Learning","date":"2022-03-28","arxiv_id":"2203.14932","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["zbr17/avsl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/attributable-visual-similarity-learning#ran","syntology_url":"https://syntology.ai/paper/2203.14932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14932"}}}},{"paper":"/paper/hyperbolic-vision-transformers-combining","slug":"hyperbolic-vision-transformers-combining","title":"Hyperbolic Vision Transformers: Combining Improvements in Metric Learning","date":"2022-03-21","arxiv_id":"2203.10833","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["htdt/hyp_metric"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hyperbolic-vision-transformers-combining#ran","syntology_url":"https://syntology.ai/paper/2203.10833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10833"}}}},{"paper":"/paper/integrating-language-guidance-into-vision","slug":"integrating-language-guidance-into-vision","title":"Integrating Language Guidance into Vision-based Deep Metric Learning","date":"2022-03-16","arxiv_id":"2203.08543","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["explainableml/languageguidance_for_dml"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/integrating-language-guidance-into-vision#ran","syntology_url":"https://syntology.ai/paper/2203.08543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08543"}}}},{"paper":"/paper/non-isotropy-regularization-for-proxy-based","slug":"non-isotropy-regularization-for-proxy-based","title":"Non-isotropy Regularization for Proxy-based Deep Metric Learning","date":"2022-03-16","arxiv_id":"2203.08547","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["explainableml/nonisotropicproxydml"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/non-isotropy-regularization-for-proxy-based#ran","syntology_url":"https://syntology.ai/paper/2203.08547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08547"}}}},{"paper":"/paper/dissecting-the-impact-of-different-loss","slug":"dissecting-the-impact-of-different-loss","title":"Dissecting the impact of different loss functions with gradient surgery","date":"2022-01-27","arxiv_id":"2201.11307","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/recall-k-surrogate-loss-with-large-batches","slug":"recall-k-surrogate-loss-with-large-batches","title":"Recall@k Surrogate Loss with Large Batches and Similarity Mixup","date":"2021-08-25","arxiv_id":"2108.11179","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["yash0307/RecallatK_surrogate","yash0307/recallatk"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/recall-k-surrogate-loss-with-large-batches#ran","syntology_url":"https://syntology.ai/paper/2108.11179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.11179"}}}},{"paper":"/paper/towards-interpretable-deep-metric-learning","slug":"towards-interpretable-deep-metric-learning","title":"Towards Interpretable Deep Metric Learning with Structural Matching","date":"2021-08-12","arxiv_id":"2108.05889","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["wl-zhao/diml"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/towards-interpretable-deep-metric-learning#ran","syntology_url":"https://syntology.ai/paper/2108.05889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.05889"}}}},{"paper":"/paper/it-takes-two-to-tango-mixup-for-deep-metric","slug":"it-takes-two-to-tango-mixup-for-deep-metric","title":"It Takes Two to Tango: Mixup for Deep Metric Learning","date":"2021-06-09","arxiv_id":"2106.04990","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["billpsomas/Metrix_ICLR22"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/it-takes-two-to-tango-mixup-for-deep-metric#ran","syntology_url":"https://syntology.ai/paper/2106.04990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04990"}}}},{"paper":"/paper/learning-intra-batch-connections-for-deep","slug":"learning-intra-batch-connections-for-deep","title":"Learning Intra-Batch Connections for Deep Metric Learning","date":"2021-02-15","arxiv_id":"2102.07753","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/s2sd-simultaneous-similarity-based-self","slug":"s2sd-simultaneous-similarity-based-self","title":"S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning","date":"2020-09-17","arxiv_id":"2009.08348","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["MLforHealth/S2SD"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/s2sd-simultaneous-similarity-based-self#ran","syntology_url":"https://syntology.ai/paper/2009.08348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.08348"}}}},{"paper":"/paper/hard-negative-examples-are-hard-but-useful","slug":"hard-negative-examples-are-hard-but-useful","title":"Hard negative examples are hard, but useful","date":"2020-07-24","arxiv_id":"2007.12749","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/calibrated-neighborhood-aware-confidence","slug":"calibrated-neighborhood-aware-confidence","title":"Calibrated neighborhood aware confidence measure for deep metric learning","date":"2020-06-08","arxiv_id":"2006.04935","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/diva-diverse-visual-feature-aggregation","slug":"diva-diverse-visual-feature-aggregation","title":"DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning","date":"2020-04-28","arxiv_id":"2004.13458","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["Confusezius/ECCV2020_DiVA_MultiFeature_DML"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diva-diverse-visual-feature-aggregation#ran","syntology_url":"https://syntology.ai/paper/2004.13458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13458"}}}},{"paper":"/paper/proxynca-revisiting-and-revitalizing-proxy","slug":"proxynca-revisiting-and-revitalizing-proxy","title":"ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis","date":"2020-04-02","arxiv_id":"2004.01113","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/proxynca-revisiting-and-revitalizing-proxy#ran","syntology_url":"https://syntology.ai/paper/2004.01113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01113"}}}},{"paper":"/paper/proxy-anchor-loss-for-deep-metric-learning","slug":"proxy-anchor-loss-for-deep-metric-learning","title":"Proxy Anchor Loss for Deep Metric Learning","date":"2020-03-31","arxiv_id":"2003.13911","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/pads-policy-adapted-sampling-for-visual","slug":"pads-policy-adapted-sampling-for-visual","title":"PADS: Policy-Adapted Sampling for Visual Similarity Learning","date":"2020-03-24","arxiv_id":"2003.11113","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["Confusezius/CVPR2020_PADS"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pads-policy-adapted-sampling-for-visual#ran","syntology_url":"https://syntology.ai/paper/2003.11113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.11113"}}}},{"paper":"/paper/metric-learning-cross-entropy-vs-pairwise","slug":"metric-learning-cross-entropy-vs-pairwise","title":"A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses","date":"2020-03-19","arxiv_id":"2003.08983","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["jeromerony/dml_cross_entropy"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/metric-learning-cross-entropy-vs-pairwise#ran","syntology_url":"https://syntology.ai/paper/2003.08983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.08983"}}}},{"paper":"/paper/circle-loss-a-unified-perspective-of-pair","slug":"circle-loss-a-unified-perspective-of-pair","title":"Circle Loss: A Unified Perspective of Pair Similarity Optimization","date":"2020-02-25","arxiv_id":"2002.10857","rows_on_this_dataset":1,"code_links":16,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/circle-loss-a-unified-perspective-of-pair#ran","syntology_url":"https://syntology.ai/paper/2002.10857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10857"}}}},{"paper":"/paper/the-group-loss-for-deep-metric-learning","slug":"the-group-loss-for-deep-metric-learning","title":"The Group Loss for Deep Metric Learning","date":"2019-12-01","arxiv_id":"1912.00385","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":2,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["dvl-tum/group_loss"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/the-group-loss-for-deep-metric-learning#ran","syntology_url":"https://syntology.ai/paper/1912.00385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00385"}}}},{"paper":"/paper/mic-mining-interclass-characteristics-for","slug":"mic-mining-interclass-characteristics-for","title":"MIC: Mining Interclass Characteristics for Improved Metric Learning","date":"2019-09-25","arxiv_id":"1909.11574","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/softtriple-loss-deep-metric-learning-without","slug":"softtriple-loss-deep-metric-learning-without","title":"SoftTriple Loss: Deep Metric Learning Without Triplet Sampling","date":"2019-09-11","arxiv_id":"1909.05235","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["idstcv/SoftTriple"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/softtriple-loss-deep-metric-learning-without#ran","syntology_url":"https://syntology.ai/paper/1909.05235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05235"}}}},{"paper":"/paper/metric-learning-with-horde-high-order","slug":"metric-learning-with-horde-high-order","title":"Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings","date":"2019-08-07","arxiv_id":"1908.02735","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["pierre-jacob/ICCV2019-Horde"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/metric-learning-with-horde-high-order#ran","syntology_url":"https://syntology.ai/paper/1908.02735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02735"}}}},{"paper":"/paper/multi-similarity-loss-with-general-pair","slug":"multi-similarity-loss-with-general-pair","title":"Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning","date":"2019-04-14","arxiv_id":"1904.06627","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["MalongTech/research-ms-loss"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-similarity-loss-with-general-pair#ran","syntology_url":"https://syntology.ai/paper/1904.06627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.06627"}}}},{"paper":"/paper/improved-embeddings-with-easy-positive","slug":"improved-embeddings-with-easy-positive","title":"Improved Embeddings with Easy Positive Triplet Mining","date":"2019-04-08","arxiv_id":"1904.04370","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["littleredxh/EasyPositiveHardNegative"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improved-embeddings-with-easy-positive#ran","syntology_url":"https://syntology.ai/paper/1904.04370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.04370"}}}},{"paper":"/paper/combination-of-multiple-global-descriptors","slug":"combination-of-multiple-global-descriptors","title":"Combination of Multiple Global Descriptors for Image Retrieval","date":"2019-03-26","arxiv_id":"1903.10663","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["naver/cgd"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/combination-of-multiple-global-descriptors#ran","syntology_url":"https://syntology.ai/paper/1903.10663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.10663"}}}},{"paper":"/paper/hardness-aware-deep-metric-learning","slug":"hardness-aware-deep-metric-learning","title":"Hardness-Aware Deep Metric Learning","date":"2019-03-13","arxiv_id":"1903.05503","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["wzzheng/HDML"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hardness-aware-deep-metric-learning#ran","syntology_url":"https://syntology.ai/paper/1903.05503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.05503"}}}},{"paper":"/paper/making-classification-competitive-for-deep","slug":"making-classification-competitive-for-deep","title":"Classification is a Strong Baseline for Deep Metric Learning","date":"2018-11-30","arxiv_id":"1811.12649","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["azgo14/classification_metric_learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/making-classification-competitive-for-deep#ran","syntology_url":"https://syntology.ai/paper/1811.12649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12649"}}}},{"paper":"/paper/deep-metric-learning-with-hierarchical","slug":"deep-metric-learning-with-hierarchical","title":"Deep Metric Learning with Hierarchical Triplet Loss","date":"2018-10-16","arxiv_id":"1810.06951","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/attention-based-ensemble-for-deep-metric","slug":"attention-based-ensemble-for-deep-metric","title":"Attention-based Ensemble for Deep Metric Learning","date":"2018-04-02","arxiv_id":"1804.00382","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sampling-matters-in-deep-embedding-learning","slug":"sampling-matters-in-deep-embedding-learning","title":"Sampling Matters in Deep Embedding Learning","date":"2017-06-23","arxiv_id":"1706.07567","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sampling-matters-in-deep-embedding-learning#ran","syntology_url":"https://syntology.ai/paper/1706.07567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.07567"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/learning-semantic-proxies-from-visual-prompts","slug":"learning-semantic-proxies-from-visual-prompts","title":"Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning","date":"2024-02-04","arxiv_id":"2402.02340","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":3,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["noahsark/parameterefficient-dml"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-semantic-proxies-from-visual-prompts#ran","syntology_url":"https://syntology.ai/paper/2402.02340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02340"}}}},{"paper":"/paper/center-contrastive-loss-for-metric-learning","slug":"center-contrastive-loss-for-metric-learning","title":"Center Contrastive Loss for Metric Learning","date":"2023-08-01","arxiv_id":"2308.00458","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mes-loss-mutually-equidistant-separation","slug":"mes-loss-mutually-equidistant-separation","title":"MES-Loss: Mutually equidistant separation metric learning loss function","date":"2023-08-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/unicom-universal-and-compact-representation","slug":"unicom-universal-and-compact-representation","title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","date":"2023-04-12","arxiv_id":"2304.05884","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":6,"official":{"repos":["deepglint/unicom"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unicom-universal-and-compact-representation#ran","syntology_url":"https://syntology.ai/paper/2304.05884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05884"}}}},{"paper":"/paper/a-continual-development-methodology-for-large","slug":"a-continual-development-methodology-for-large","title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","date":"2022-09-15","arxiv_id":"2209.07326","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/das-densely-anchored-sampling-for-deep-metric","slug":"das-densely-anchored-sampling-for-deep-metric","title":"DAS: Densely-Anchored Sampling for Deep Metric Learning","date":"2022-07-30","arxiv_id":"2208.00119","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["lizhaoliu-Lec/DAS"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/das-densely-anchored-sampling-for-deep-metric#ran","syntology_url":"https://syntology.ai/paper/2208.00119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.00119"}}}},{"paper":"/paper/attributable-visual-similarity-learning","slug":"attributable-visual-similarity-learning","title":"Attributable Visual Similarity Learning","date":"2022-03-28","arxiv_id":"2203.14932","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["zbr17/avsl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/attributable-visual-similarity-learning#ran","syntology_url":"https://syntology.ai/paper/2203.14932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14932"}}}},{"paper":"/paper/hyperbolic-vision-transformers-combining","slug":"hyperbolic-vision-transformers-combining","title":"Hyperbolic Vision Transformers: Combining Improvements in Metric Learning","date":"2022-03-21","arxiv_id":"2203.10833","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["htdt/hyp_metric"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hyperbolic-vision-transformers-combining#ran","syntology_url":"https://syntology.ai/paper/2203.10833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10833"}}}},{"paper":"/paper/integrating-language-guidance-into-vision","slug":"integrating-language-guidance-into-vision","title":"Integrating Language Guidance into Vision-based Deep Metric Learning","date":"2022-03-16","arxiv_id":"2203.08543","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["explainableml/languageguidance_for_dml"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/integrating-language-guidance-into-vision#ran","syntology_url":"https://syntology.ai/paper/2203.08543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08543"}}}},{"paper":"/paper/non-isotropy-regularization-for-proxy-based","slug":"non-isotropy-regularization-for-proxy-based","title":"Non-isotropy Regularization for Proxy-based Deep Metric Learning","date":"2022-03-16","arxiv_id":"2203.08547","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["explainableml/nonisotropicproxydml"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/non-isotropy-regularization-for-proxy-based#ran","syntology_url":"https://syntology.ai/paper/2203.08547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08547"}}}},{"paper":"/paper/dissecting-the-impact-of-different-loss","slug":"dissecting-the-impact-of-different-loss","title":"Dissecting the impact of different loss functions with gradient surgery","date":"2022-01-27","arxiv_id":"2201.11307","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/recall-k-surrogate-loss-with-large-batches","slug":"recall-k-surrogate-loss-with-large-batches","title":"Recall@k Surrogate Loss with Large Batches and Similarity Mixup","date":"2021-08-25","arxiv_id":"2108.11179","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["yash0307/RecallatK_surrogate","yash0307/recallatk"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/recall-k-surrogate-loss-with-large-batches#ran","syntology_url":"https://syntology.ai/paper/2108.11179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.11179"}}}},{"paper":"/paper/towards-interpretable-deep-metric-learning","slug":"towards-interpretable-deep-metric-learning","title":"Towards Interpretable Deep Metric Learning with Structural Matching","date":"2021-08-12","arxiv_id":"2108.05889","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["wl-zhao/diml"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/towards-interpretable-deep-metric-learning#ran","syntology_url":"https://syntology.ai/paper/2108.05889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.05889"}}}},{"paper":"/paper/it-takes-two-to-tango-mixup-for-deep-metric","slug":"it-takes-two-to-tango-mixup-for-deep-metric","title":"It Takes Two to Tango: Mixup for Deep Metric Learning","date":"2021-06-09","arxiv_id":"2106.04990","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["billpsomas/Metrix_ICLR22"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/it-takes-two-to-tango-mixup-for-deep-metric#ran","syntology_url":"https://syntology.ai/paper/2106.04990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04990"}}}},{"paper":"/paper/learning-intra-batch-connections-for-deep","slug":"learning-intra-batch-connections-for-deep","title":"Learning Intra-Batch Connections for Deep Metric Learning","date":"2021-02-15","arxiv_id":"2102.07753","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/s2sd-simultaneous-similarity-based-self","slug":"s2sd-simultaneous-similarity-based-self","title":"S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning","date":"2020-09-17","arxiv_id":"2009.08348","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["MLforHealth/S2SD"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/s2sd-simultaneous-similarity-based-self#ran","syntology_url":"https://syntology.ai/paper/2009.08348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.08348"}}}},{"paper":"/paper/hard-negative-examples-are-hard-but-useful","slug":"hard-negative-examples-are-hard-but-useful","title":"Hard negative examples are hard, but useful","date":"2020-07-24","arxiv_id":"2007.12749","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/calibrated-neighborhood-aware-confidence","slug":"calibrated-neighborhood-aware-confidence","title":"Calibrated neighborhood aware confidence measure for deep metric learning","date":"2020-06-08","arxiv_id":"2006.04935","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/diva-diverse-visual-feature-aggregation","slug":"diva-diverse-visual-feature-aggregation","title":"DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning","date":"2020-04-28","arxiv_id":"2004.13458","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["Confusezius/ECCV2020_DiVA_MultiFeature_DML"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diva-diverse-visual-feature-aggregation#ran","syntology_url":"https://syntology.ai/paper/2004.13458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13458"}}}},{"paper":"/paper/proxynca-revisiting-and-revitalizing-proxy","slug":"proxynca-revisiting-and-revitalizing-proxy","title":"ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis","date":"2020-04-02","arxiv_id":"2004.01113","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/proxynca-revisiting-and-revitalizing-proxy#ran","syntology_url":"https://syntology.ai/paper/2004.01113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01113"}}}},{"paper":"/paper/proxy-anchor-loss-for-deep-metric-learning","slug":"proxy-anchor-loss-for-deep-metric-learning","title":"Proxy Anchor Loss for Deep Metric Learning","date":"2020-03-31","arxiv_id":"2003.13911","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/pads-policy-adapted-sampling-for-visual","slug":"pads-policy-adapted-sampling-for-visual","title":"PADS: Policy-Adapted Sampling for Visual Similarity Learning","date":"2020-03-24","arxiv_id":"2003.11113","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["Confusezius/CVPR2020_PADS"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pads-policy-adapted-sampling-for-visual#ran","syntology_url":"https://syntology.ai/paper/2003.11113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.11113"}}}},{"paper":"/paper/metric-learning-cross-entropy-vs-pairwise","slug":"metric-learning-cross-entropy-vs-pairwise","title":"A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses","date":"2020-03-19","arxiv_id":"2003.08983","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["jeromerony/dml_cross_entropy"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/metric-learning-cross-entropy-vs-pairwise#ran","syntology_url":"https://syntology.ai/paper/2003.08983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.08983"}}}},{"paper":"/paper/circle-loss-a-unified-perspective-of-pair","slug":"circle-loss-a-unified-perspective-of-pair","title":"Circle Loss: A Unified Perspective of Pair Similarity Optimization","date":"2020-02-25","arxiv_id":"2002.10857","rows_on_this_dataset":1,"code_links":16,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/circle-loss-a-unified-perspective-of-pair#ran","syntology_url":"https://syntology.ai/paper/2002.10857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10857"}}}},{"paper":"/paper/the-group-loss-for-deep-metric-learning","slug":"the-group-loss-for-deep-metric-learning","title":"The Group Loss for Deep Metric Learning","date":"2019-12-01","arxiv_id":"1912.00385","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":2,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["dvl-tum/group_loss"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/the-group-loss-for-deep-metric-learning#ran","syntology_url":"https://syntology.ai/paper/1912.00385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00385"}}}},{"paper":"/paper/mic-mining-interclass-characteristics-for","slug":"mic-mining-interclass-characteristics-for","title":"MIC: Mining Interclass Characteristics for Improved Metric Learning","date":"2019-09-25","arxiv_id":"1909.11574","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/softtriple-loss-deep-metric-learning-without","slug":"softtriple-loss-deep-metric-learning-without","title":"SoftTriple Loss: Deep Metric Learning Without Triplet Sampling","date":"2019-09-11","arxiv_id":"1909.05235","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["idstcv/SoftTriple"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/softtriple-loss-deep-metric-learning-without#ran","syntology_url":"https://syntology.ai/paper/1909.05235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05235"}}}},{"paper":"/paper/metric-learning-with-horde-high-order","slug":"metric-learning-with-horde-high-order","title":"Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings","date":"2019-08-07","arxiv_id":"1908.02735","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["pierre-jacob/ICCV2019-Horde"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/metric-learning-with-horde-high-order#ran","syntology_url":"https://syntology.ai/paper/1908.02735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02735"}}}},{"paper":"/paper/multi-similarity-loss-with-general-pair","slug":"multi-similarity-loss-with-general-pair","title":"Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning","date":"2019-04-14","arxiv_id":"1904.06627","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["MalongTech/research-ms-loss"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-similarity-loss-with-general-pair#ran","syntology_url":"https://syntology.ai/paper/1904.06627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.06627"}}}},{"paper":"/paper/improved-embeddings-with-easy-positive","slug":"improved-embeddings-with-easy-positive","title":"Improved Embeddings with Easy Positive Triplet Mining","date":"2019-04-08","arxiv_id":"1904.04370","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["littleredxh/EasyPositiveHardNegative"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improved-embeddings-with-easy-positive#ran","syntology_url":"https://syntology.ai/paper/1904.04370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.04370"}}}},{"paper":"/paper/combination-of-multiple-global-descriptors","slug":"combination-of-multiple-global-descriptors","title":"Combination of Multiple Global Descriptors for Image Retrieval","date":"2019-03-26","arxiv_id":"1903.10663","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["naver/cgd"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/combination-of-multiple-global-descriptors#ran","syntology_url":"https://syntology.ai/paper/1903.10663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.10663"}}}},{"paper":"/paper/hardness-aware-deep-metric-learning","slug":"hardness-aware-deep-metric-learning","title":"Hardness-Aware Deep Metric Learning","date":"2019-03-13","arxiv_id":"1903.05503","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["wzzheng/HDML"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hardness-aware-deep-metric-learning#ran","syntology_url":"https://syntology.ai/paper/1903.05503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.05503"}}}},{"paper":"/paper/making-classification-competitive-for-deep","slug":"making-classification-competitive-for-deep","title":"Classification is a Strong Baseline for Deep Metric Learning","date":"2018-11-30","arxiv_id":"1811.12649","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["azgo14/classification_metric_learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/making-classification-competitive-for-deep#ran","syntology_url":"https://syntology.ai/paper/1811.12649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12649"}}}},{"paper":"/paper/deep-metric-learning-with-hierarchical","slug":"deep-metric-learning-with-hierarchical","title":"Deep Metric Learning with Hierarchical Triplet Loss","date":"2018-10-16","arxiv_id":"1810.06951","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/attention-based-ensemble-for-deep-metric","slug":"attention-based-ensemble-for-deep-metric","title":"Attention-based Ensemble for Deep Metric Learning","date":"2018-04-02","arxiv_id":"1804.00382","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sampling-matters-in-deep-embedding-learning","slug":"sampling-matters-in-deep-embedding-learning","title":"Sampling Matters in Deep Embedding Learning","date":"2017-06-23","arxiv_id":"1706.07567","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sampling-matters-in-deep-embedding-learning#ran","syntology_url":"https://syntology.ai/paper/1706.07567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.07567"}}}}],"papers_where_code_ran":22,"papers_where_code_ran_first_page":"/dataset/cars196/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/cars196/papers/ran/1","json":"/dataset/cars196/papers/ran/1.json","rows":22}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":25,"samples_harvested":117,"samples_ran":75,"samples_constructed":3,"samples_ran_checked":59,"samples_ran_instrument_failed":16,"samples_unverified":42,"pointer_only_for_licence":15,"papers_with_no_sample_that_ran":3,"papers_with_a_sample_that_ran":22,"papers_with_a_run_with_no_instrument_failure":19,"papers_where_every_run_was_an_instrument_failure":3,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"715b45ae0cb47e05cbcfd0a0994b2c1ce745ab90592d8f12d85bdb8441e61829","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}