{"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":"/task/zero-shot-image-classification","name":"Zero-Shot Image Classification","slug":"zero-shot-image-classification","description_markdown":"Zero-shot image classification is a technique in computer vision where a model can classify images into categories that were not present during training. This is achieved by leveraging semantic information about the categories, such as textual descriptions or relationships between classes.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":111,"papers_with_code":64,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":6,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/zero-shot-image-classification-on-country211","slug":"zero-shot-image-classification-on-country211","dataset":"Country211","dataset_url":"/dataset/country211","rows_in_archive":1,"metrics":["Top-1 accuracy"],"first_row_in_archive_order":{"model":"OpenClip H/14 (34B)(Laion2B)","paper_title":"Reproducible scaling laws for contrastive language-image learning","paper_url":"/paper/reproducible-scaling-laws-for-contrastive","paper_date":"2022-12-14","arxiv_id":"2212.07143","code_links":[{"title":"mlfoundations/open_clip","url":"https://github.com/mlfoundations/open_clip"},{"title":"laion-ai/scaling-laws-openclip","url":"https://github.com/laion-ai/scaling-laws-openclip"},{"title":"shkarupa-alex/tfclip","url":"https://github.com/shkarupa-alex/tfclip"},{"title":"nahidalam/open_clip","url":"https://github.com/nahidalam/open_clip"},{"title":"eify/open_clip","url":"https://github.com/eify/open_clip"}],"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reproducible-scaling-laws-for-contrastive#ran","syntology_url":"https://syntology.ai/paper/2212.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07143"}},"official":{"repos":["laion-ai/scaling-laws-openclip"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/zero-shot-image-classification-on-icinw","slug":"zero-shot-image-classification-on-icinw","dataset":"ICinW","dataset_url":null,"rows_in_archive":1,"metrics":["Average Score"],"first_row_in_archive_order":{"model":"CLIP (ViT B-32)","paper_title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","paper_url":"/paper/elevater-a-benchmark-and-toolkit-for","paper_date":"2022-04-19","arxiv_id":"2204.08790","code_links":[{"title":"microsoft/GLIP","url":"https://github.com/microsoft/GLIP"},{"title":"computer-vision-in-the-wild/cvinw_readings","url":"https://github.com/computer-vision-in-the-wild/cvinw_readings"},{"title":"microsoft/esvit","url":"https://github.com/microsoft/esvit"},{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"eric-ai-lab/pevit","url":"https://github.com/eric-ai-lab/pevit"},{"title":"Computer-Vision-in-the-Wild/Elevater_Toolkit_IC","url":"https://github.com/Computer-Vision-in-the-Wild/Elevater_Toolkit_IC"},{"title":"sincerass/mvlpt","url":"https://github.com/sincerass/mvlpt"},{"title":"microsoft/klite","url":"https://github.com/microsoft/klite"},{"title":"rsCPSyEu/ovd_cod","url":"https://github.com/rsCPSyEu/ovd_cod"}],"syntology":{"n":20,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/elevater-a-benchmark-and-toolkit-for#ran","syntology_url":"https://syntology.ai/paper/2204.08790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08790"}},"official":{"repos":["Computer-Vision-in-the-Wild/Elevater_Toolkit_IC","computer-vision-in-the-wild/cvinw_readings"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/zero-shot-image-classification-on-odinw","slug":"zero-shot-image-classification-on-odinw","dataset":"ODinW","dataset_url":null,"rows_in_archive":1,"metrics":["Average Score"],"first_row_in_archive_order":{"model":"GLIP (Tiny A)","paper_title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","paper_url":"/paper/elevater-a-benchmark-and-toolkit-for","paper_date":"2022-04-19","arxiv_id":"2204.08790","code_links":[{"title":"microsoft/GLIP","url":"https://github.com/microsoft/GLIP"},{"title":"computer-vision-in-the-wild/cvinw_readings","url":"https://github.com/computer-vision-in-the-wild/cvinw_readings"},{"title":"microsoft/esvit","url":"https://github.com/microsoft/esvit"},{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"eric-ai-lab/pevit","url":"https://github.com/eric-ai-lab/pevit"},{"title":"Computer-Vision-in-the-Wild/Elevater_Toolkit_IC","url":"https://github.com/Computer-Vision-in-the-Wild/Elevater_Toolkit_IC"},{"title":"sincerass/mvlpt","url":"https://github.com/sincerass/mvlpt"},{"title":"microsoft/klite","url":"https://github.com/microsoft/klite"},{"title":"rsCPSyEu/ovd_cod","url":"https://github.com/rsCPSyEu/ovd_cod"}],"syntology":{"n":20,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/elevater-a-benchmark-and-toolkit-for#ran","syntology_url":"https://syntology.ai/paper/2204.08790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08790"}},"official":{"repos":["Computer-Vision-in-the-Wild/Elevater_Toolkit_IC","computer-vision-in-the-wild/cvinw_readings"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["listed","official"]}}}}],"datasets":[{"url":"/dataset/quilt-1m","name":"QUILT-1M","full_name":"","num_papers_in_archive":17},{"url":"/dataset/country211","name":"Country211","full_name":"Country211","num_papers_in_archive":3},{"url":"/dataset/mineralimage5k","name":"MineralImage5k","full_name":"Benchmark for 5k raw mineral species recognition","num_papers_in_archive":1},{"url":"/dataset/ovic-datasets","name":"OVIC Datasets","full_name":"Open Vocabulary Image Classification Datasets","num_papers_in_archive":1},{"url":"/dataset/taxabench-8k","name":"TaxaBench-8k","full_name":"","num_papers_in_archive":1},{"url":"/dataset/corn-seeds-dataset","name":"Corn Seeds Dataset","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/open-vocabulary-image-classification","name":"Open Vocabulary Image Classification"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":111,"of_with_code":64,"tagged_in_all":111,"counts":{"archive_papers_tagged":111,"with_a_code_link":64,"where_syntology_ran_a_sample":25,"not_listed_spam_title":0,"listed":111,"listed_where_code_ran":25,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":20,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":20,"listed_every_run_a_failure_of_syntologys_instrument":5,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/elevater-a-benchmark-and-toolkit-for","slug":"elevater-a-benchmark-and-toolkit-for","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","date":"2022-04-19","arxiv_id":"2204.08790","repositories_listed":9,"syntology":{"n":20,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/elevater-a-benchmark-and-toolkit-for#ran","syntology_url":"https://syntology.ai/paper/2204.08790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08790"}},"official":{"repos":["Computer-Vision-in-the-Wild/Elevater_Toolkit_IC","computer-vision-in-the-wild/cvinw_readings"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/reproducible-scaling-laws-for-contrastive","slug":"reproducible-scaling-laws-for-contrastive","title":"Reproducible scaling laws for contrastive language-image learning","date":"2022-12-14","arxiv_id":"2212.07143","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reproducible-scaling-laws-for-contrastive#ran","syntology_url":"https://syntology.ai/paper/2212.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07143"}},"official":{"repos":["laion-ai/scaling-laws-openclip"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/lit-zero-shot-transfer-with-locked-image-text","slug":"lit-zero-shot-transfer-with-locked-image-text","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","date":"2021-11-15","arxiv_id":"2111.07991","repositories_listed":5,"syntology":null},{"url":"/paper/scaling-up-visual-and-vision-language","slug":"scaling-up-visual-and-vision-language","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","date":"2021-02-11","arxiv_id":"2102.05918","repositories_listed":5,"syntology":{"n":10,"n_ran":8,"n_constructed":6,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scaling-up-visual-and-vision-language#ran","syntology_url":"https://syntology.ai/paper/2102.05918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05918"}},"official":null}},{"url":"/paper/zero-shot-detection-via-vision-and-language","slug":"zero-shot-detection-via-vision-and-language","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","date":"2021-04-28","arxiv_id":"2104.13921","repositories_listed":4,"syntology":null},{"url":"/paper/what-does-a-platypus-look-like-generating","slug":"what-does-a-platypus-look-like-generating","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","date":"2022-09-07","arxiv_id":"2209.03320","repositories_listed":3,"syntology":null},{"url":"/paper/unconstrained-open-vocabulary-image","slug":"unconstrained-open-vocabulary-image","title":"Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion","date":"2024-07-15","arxiv_id":"2407.11211","repositories_listed":2,"syntology":null},{"url":"/paper/sparse-concept-bottleneck-models-gumbel","slug":"sparse-concept-bottleneck-models-gumbel","title":"Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning","date":"2024-04-04","arxiv_id":"2404.03323","repositories_listed":2,"syntology":null},{"url":"/paper/contrasting-intra-modal-and-ranking-cross","slug":"contrasting-intra-modal-and-ranking-cross","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","date":"2023-06-15","arxiv_id":"2306.08832","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contrasting-intra-modal-and-ranking-cross#ran","syntology_url":"https://syntology.ai/paper/2306.08832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08832"}},"official":{"repos":["lezhang7/Enhance-FineGrained","magiccircuit/enhance-finegrained"],"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"]}}},{"url":"/paper/altclip-altering-the-language-encoder-in-clip","slug":"altclip-altering-the-language-encoder-in-clip","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","date":"2022-11-12","arxiv_id":"2211.06679","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/altclip-altering-the-language-encoder-in-clip#ran","syntology_url":"https://syntology.ai/paper/2211.06679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.06679"}},"official":{"repos":["flagai-open/flagai"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/duet-cross-modal-semantic-grounding-for","slug":"duet-cross-modal-semantic-grounding-for","title":"DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning","date":"2022-07-04","arxiv_id":"2207.01328","repositories_listed":2,"syntology":null},{"url":"/paper/2112-14757","slug":"2112-14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","date":"2021-12-29","arxiv_id":"2112.14757","repositories_listed":2,"syntology":null},{"url":"/paper/lrsclip-a-vision-language-foundation-model","slug":"lrsclip-a-vision-language-foundation-model","title":"LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text","date":"2025-03-25","arxiv_id":"2503.19311","repositories_listed":1,"syntology":null},{"url":"/paper/cross-the-gap-exposing-the-intra-modal","slug":"cross-the-gap-exposing-the-intra-modal","title":"Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion","date":"2025-02-06","arxiv_id":"2502.04263","repositories_listed":1,"syntology":null},{"url":"/paper/kpl-training-free-medical-knowledge-mining-of","slug":"kpl-training-free-medical-knowledge-mining-of","title":"KPL: Training-Free Medical Knowledge Mining of Vision-Language Models","date":"2025-01-20","arxiv_id":"2501.11231","repositories_listed":1,"syntology":null},{"url":"/paper/post-hoc-probabilistic-vision-language-models","slug":"post-hoc-probabilistic-vision-language-models","title":"Post-hoc Probabilistic Vision-Language Models","date":"2024-12-08","arxiv_id":"2412.06014","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":6,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/post-hoc-probabilistic-vision-language-models#ran","syntology_url":"https://syntology.ai/paper/2412.06014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06014"}},"official":{"repos":["AaltoML/BayesVLM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/taxabind-a-unified-embedding-space-for","slug":"taxabind-a-unified-embedding-space-for","title":"TaxaBind: A Unified Embedding Space for Ecological Applications","date":"2024-11-01","arxiv_id":"2411.00683","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/taxabind-a-unified-embedding-space-for#ran","syntology_url":"https://syntology.ai/paper/2411.00683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00683"}},"official":{"repos":["mvrl/taxabind"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multilingual-vision-language-pre-training-for","slug":"multilingual-vision-language-pre-training-for","title":"Multilingual Vision-Language Pre-training for the Remote Sensing Domain","date":"2024-10-30","arxiv_id":"2410.23370","repositories_listed":1,"syntology":null},{"url":"/paper/altogether-image-captioning-via-re-aligning","slug":"altogether-image-captioning-via-re-aligning","title":"Altogether: Image Captioning via Re-aligning Alt-text","date":"2024-10-22","arxiv_id":"2410.17251","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/altogether-image-captioning-via-re-aligning#ran","syntology_url":"https://syntology.ai/paper/2410.17251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17251"}},"official":{"repos":["facebookresearch/metaclip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/open-vocabulary-vs-closed-set-best-practice","slug":"open-vocabulary-vs-closed-set-best-practice","title":"Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability","date":"2024-10-20","arxiv_id":"2410.15315","repositories_listed":1,"syntology":null},{"url":"/paper/interpreting-and-analyzing-clip-s-zero-shot","slug":"interpreting-and-analyzing-clip-s-zero-shot","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","date":"2024-10-16","arxiv_id":"2410.13016","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interpreting-and-analyzing-clip-s-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2410.13016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13016"}},"official":{"repos":["fawazsammani/clip-interpret-mutual-knowledge"],"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"]}}},{"url":"/paper/clip-moe-towards-building-mixture-of-experts","slug":"clip-moe-towards-building-mixture-of-experts","title":"CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling","date":"2024-09-28","arxiv_id":"2409.19291","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clip-moe-towards-building-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2409.19291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19291"}},"official":{"repos":["OpenSparseLLMs/CLIP-MoE"],"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"]}}},{"url":"/paper/dpa-dual-prototypes-alignment-for","slug":"dpa-dual-prototypes-alignment-for","title":"DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models","date":"2024-08-16","arxiv_id":"2408.08855","repositories_listed":1,"syntology":null},{"url":"/paper/do-vision-language-foundational-models-show","slug":"do-vision-language-foundational-models-show","title":"Do Vision-Language Foundational models show Robust Visual Perception?","date":"2024-08-13","arxiv_id":"2408.06781","repositories_listed":1,"syntology":null},{"url":"/paper/pathgen-1-6m-1-6-million-pathology-image-text","slug":"pathgen-1-6m-1-6-million-pathology-image-text","title":"PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration","date":"2024-06-28","arxiv_id":"2407.00203","repositories_listed":1,"syntology":null},{"url":"/paper/mitigate-the-gap-investigating-approaches-for","slug":"mitigate-the-gap-investigating-approaches-for","title":"Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP","date":"2024-06-25","arxiv_id":"2406.17639","repositories_listed":1,"syntology":{"n":22,"n_ran":16,"n_constructed":0,"n_ran_checked":9,"n_instrument":7,"n_unverified":6,"n_honours":0,"n_violates":3,"n_no_contract":6,"n_pointer_only":22,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 3 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mitigate-the-gap-investigating-approaches-for#ran","syntology_url":"https://syntology.ai/paper/2406.17639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17639"}},"official":{"repos":["sarahesl/alignclip"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/watt-weight-average-test-time-adaption-of","slug":"watt-weight-average-test-time-adaption-of","title":"WATT: Weight Average Test-Time Adaptation of CLIP","date":"2024-06-19","arxiv_id":"2406.13875","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/watt-weight-average-test-time-adaption-of#ran","syntology_url":"https://syntology.ai/paper/2406.13875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13875"}},"official":{"repos":["mehrdad-noori/watt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mind-s-eye-image-recognition-by-eeg-via","slug":"mind-s-eye-image-recognition-by-eeg-via","title":"Mind's Eye: Image Recognition by EEG via Multimodal Similarity-Keeping Contrastive Learning","date":"2024-06-05","arxiv_id":"2406.16910","repositories_listed":1,"syntology":null},{"url":"/paper/what-do-you-see-enhancing-zero-shot-image","slug":"what-do-you-see-enhancing-zero-shot-image","title":"What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models","date":"2024-05-24","arxiv_id":"2405.15668","repositories_listed":1,"syntology":null},{"url":"/paper/who-s-in-and-who-s-out-a-case-study-of","slug":"who-s-in-and-who-s-out-a-case-study-of","title":"Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp","date":"2024-05-13","arxiv_id":"2405.08209","repositories_listed":1,"syntology":null},{"url":"/paper/mode-clip-data-experts-via-clustering","slug":"mode-clip-data-experts-via-clustering","title":"MoDE: CLIP Data Experts via Clustering","date":"2024-04-24","arxiv_id":"2404.16030","repositories_listed":1,"syntology":null},{"url":"/paper/learn-no-to-say-yes-better-improving-vision","slug":"learn-no-to-say-yes-better-improving-vision","title":"Learn \"No\" to Say \"Yes\" Better: Improving Vision-Language Models via Negations","date":"2024-03-29","arxiv_id":"2403.20312","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learn-no-to-say-yes-better-improving-vision#ran","syntology_url":"https://syntology.ai/paper/2403.20312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.20312"}},"official":{"repos":["jaisidhsingh/con-clip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/are-vision-language-models-texture-or-shape","slug":"are-vision-language-models-texture-or-shape","title":"Can We Talk Models Into Seeing the World Differently?","date":"2024-03-14","arxiv_id":"2403.09193","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/are-vision-language-models-texture-or-shape#ran","syntology_url":"https://syntology.ai/paper/2403.09193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09193"}},"official":{"repos":["paulgavrikov/vlm_shapebias"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/promptkd-unsupervised-prompt-distillation-for","slug":"promptkd-unsupervised-prompt-distillation-for","title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","date":"2024-03-05","arxiv_id":"2403.02781","repositories_listed":1,"syntology":null},{"url":"/paper/image-caption-encoding-for-improving-zero","slug":"image-caption-encoding-for-improving-zero","title":"Image-Caption Encoding for Improving Zero-Shot Generalization","date":"2024-02-05","arxiv_id":"2402.02662","repositories_listed":1,"syntology":null},{"url":"/paper/segment-any-change","slug":"segment-any-change","title":"Segment Any Change","date":"2024-02-02","arxiv_id":"2402.01188","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/segment-any-change#ran","syntology_url":"https://syntology.ai/paper/2402.01188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01188"}},"official":{"repos":["Z-Zheng/pytorch-change-models"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-adaptability-and-generalizability","slug":"improving-adaptability-and-generalizability","title":"Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language Models","date":"2023-11-27","arxiv_id":"2311.15569","repositories_listed":1,"syntology":null},{"url":"/paper/clipself-vision-transformer-distills-itself","slug":"clipself-vision-transformer-distills-itself","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","date":"2023-10-02","arxiv_id":"2310.01403","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/clipself-vision-transformer-distills-itself#ran","syntology_url":"https://syntology.ai/paper/2310.01403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01403"}},"official":{"repos":["wusize/clipself"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/more-context-less-distraction-visual","slug":"more-context-less-distraction-visual","title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","date":"2023-08-02","arxiv_id":"2308.01313","repositories_listed":1,"syntology":{"n":12,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/more-context-less-distraction-visual#ran","syntology_url":"https://syntology.ai/paper/2308.01313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01313"}},"official":{"repos":["umd-huang-lab/perceptionclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/promptstyler-prompt-driven-style-generation","slug":"promptstyler-prompt-driven-style-generation","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","date":"2023-07-27","arxiv_id":"2307.15199","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/promptstyler-prompt-driven-style-generation#ran","syntology_url":"https://syntology.ai/paper/2307.15199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15199"}},"official":null}},{"url":"/paper/distilling-large-vision-language-model-with","slug":"distilling-large-vision-language-model-with","title":"Distilling Large Vision-Language Model with Out-of-Distribution Generalizability","date":"2023-07-06","arxiv_id":"2307.03135","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/distilling-large-vision-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2307.03135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03135"}},"official":{"repos":["xuanlinli17/large_vlm_distillation_ood"],"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"]}}},{"url":"/paper/remoteclip-a-vision-language-foundation-model","slug":"remoteclip-a-vision-language-foundation-model","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","date":"2023-06-19","arxiv_id":"2306.11029","repositories_listed":1,"syntology":null},{"url":"/paper/babel-imagenet-massively-multilingual","slug":"babel-imagenet-massively-multilingual","title":"Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations","date":"2023-06-14","arxiv_id":"2306.08658","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/babel-imagenet-massively-multilingual#ran","syntology_url":"https://syntology.ai/paper/2306.08658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08658"}},"official":{"repos":["gregor-ge/babel-imagenet"],"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"]}}},{"url":"/paper/learning-from-children-improving-image","slug":"learning-from-children-improving-image","title":"Learning from Children: Improving Image-Caption Pretraining via Curriculum","date":"2023-05-27","arxiv_id":"2305.17540","repositories_listed":1,"syntology":null},{"url":"/paper/camdiff-camouflage-image-augmentation-via","slug":"camdiff-camouflage-image-augmentation-via","title":"CamDiff: Camouflage Image Augmentation via Diffusion Model","date":"2023-04-11","arxiv_id":"2304.05469","repositories_listed":1,"syntology":null},{"url":"/paper/text-to-image-diffusion-models-are-zero-shot","slug":"text-to-image-diffusion-models-are-zero-shot","title":"Text-to-Image Diffusion Models are Zero-Shot Classifiers","date":"2023-03-27","arxiv_id":"2303.15233","repositories_listed":1,"syntology":null},{"url":"/paper/structure-pretraining-and-prompt-tuning-for","slug":"structure-pretraining-and-prompt-tuning-for","title":"Structure Pretraining and Prompt Tuning for Knowledge Graph Transfer","date":"2023-03-03","arxiv_id":"2303.03922","repositories_listed":1,"syntology":null},{"url":"/paper/chils-zero-shot-image-classification-with","slug":"chils-zero-shot-image-classification-with","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","date":"2023-02-06","arxiv_id":"2302.02551","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/chils-zero-shot-image-classification-with#ran","syntology_url":"https://syntology.ai/paper/2302.02551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.02551"}},"official":{"repos":["acmi-lab/chils"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/anchor-based-adversarially-robust-zero-shot","slug":"anchor-based-adversarially-robust-zero-shot","title":"Language-Driven Anchors for Zero-Shot Adversarial Robustness","date":"2023-01-30","arxiv_id":"2301.13096","repositories_listed":1,"syntology":null},{"url":"/paper/lexlip-lexicon-bottlenecked-language-image-1","slug":"lexlip-lexicon-bottlenecked-language-image-1","title":"LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/image-and-language-understanding-from-pixels","slug":"image-and-language-understanding-from-pixels","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","date":"2022-12-15","arxiv_id":"2212.08045","repositories_listed":1,"syntology":null},{"url":"/paper/chinese-clip-contrastive-vision-language","slug":"chinese-clip-contrastive-vision-language","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","date":"2022-11-02","arxiv_id":"2211.01335","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chinese-clip-contrastive-vision-language#ran","syntology_url":"https://syntology.ai/paper/2211.01335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01335"}},"official":{"repos":["ofa-sys/chinese-clip"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/general-image-descriptors-for-open-world","slug":"general-image-descriptors-for-open-world","title":"General Image Descriptors for Open World Image Retrieval using ViT CLIP","date":"2022-10-20","arxiv_id":"2210.11141","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/general-image-descriptors-for-open-world#ran","syntology_url":"https://syntology.ai/paper/2210.11141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11141"}},"official":{"repos":["ivanaer/g-universal-clip"],"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"]}}},{"url":"/paper/pali-a-jointly-scaled-multilingual-language","slug":"pali-a-jointly-scaled-multilingual-language","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","date":"2022-09-14","arxiv_id":"2209.06794","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pali-a-jointly-scaled-multilingual-language#ran","syntology_url":"https://syntology.ai/paper/2209.06794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06794"}},"official":{"repos":["google-research/big_vision"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-temporal-action-detection-via","slug":"zero-shot-temporal-action-detection-via","title":"Zero-Shot Temporal Action Detection via Vision-Language Prompting","date":"2022-07-17","arxiv_id":"2207.08184","repositories_listed":1,"syntology":null},{"url":"/paper/disentangled-ontology-embedding-for-zero-shot","slug":"disentangled-ontology-embedding-for-zero-shot","title":"Disentangled Ontology Embedding for Zero-shot Learning","date":"2022-06-08","arxiv_id":"2206.03739","repositories_listed":1,"syntology":null},{"url":"/paper/masked-unsupervised-self-training-for-zero","slug":"masked-unsupervised-self-training-for-zero","title":"Masked Unsupervised Self-training for Label-free Image Classification","date":"2022-06-07","arxiv_id":"2206.02967","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/masked-unsupervised-self-training-for-zero#ran","syntology_url":"https://syntology.ai/paper/2206.02967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02967"}},"official":{"repos":["salesforce/must"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-and-r2d2-a-large-scale-chinese-cross","slug":"zero-and-r2d2-a-large-scale-chinese-cross","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","date":"2022-05-08","arxiv_id":"2205.03860","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zero-and-r2d2-a-large-scale-chinese-cross#ran","syntology_url":"https://syntology.ai/paper/2205.03860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.03860"}},"official":{"repos":["yuxie11/R2D2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-logit-adjustment","slug":"zero-shot-logit-adjustment","title":"Zero-Shot Logit Adjustment","date":"2022-04-25","arxiv_id":"2204.11822","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-hierarchical-graph-representation","slug":"exploring-hierarchical-graph-representation","title":"Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification","date":"2022-03-02","arxiv_id":"2203.01386","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/exploring-hierarchical-graph-representation#ran","syntology_url":"https://syntology.ai/paper/2203.01386","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01386"}},"official":{"repos":["WilliamYi96/HGR-Net"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/wukong-100-million-large-scale-chinese-cross","slug":"wukong-100-million-large-scale-chinese-cross","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","date":"2022-02-14","arxiv_id":"2202.06767","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/wukong-100-million-large-scale-chinese-cross#ran","syntology_url":"https://syntology.ai/paper/2202.06767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06767"}},"official":null}},{"url":"/paper/filip-fine-grained-interactive-language-image-1","slug":"filip-fine-grained-interactive-language-image-1","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","date":"2021-11-09","arxiv_id":"2111.07783","repositories_listed":1,"syntology":null},{"url":"/paper/k-zsl-resources-for-knowledge-driven-zero","slug":"k-zsl-resources-for-knowledge-driven-zero","title":"Benchmarking Knowledge-driven Zero-shot Learning","date":"2021-06-29","arxiv_id":"2106.15047","repositories_listed":1,"syntology":null},{"url":"/paper/generative-multi-label-zero-shot-learning","slug":"generative-multi-label-zero-shot-learning","title":"Generative Multi-Label Zero-Shot Learning","date":"2021-01-27","arxiv_id":"2101.11606","repositories_listed":1,"syntology":null},{"url":null,"slug":"cibr-cross-modal-information-bottleneck","title":"CIBR: Cross-modal Information Bottleneck Regularization for Robust CLIP Generalization","date":"2025-03-31","arxiv_id":"2503.24182","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-visible-multispectral-vision","title":"Beyond the Visible: Multispectral Vision-Language Learning for Earth Observation","date":"2025-03-20","arxiv_id":"2503.15969","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-test-time-adaptation-for-vision","title":"Bayesian Test-Time Adaptation for Vision-Language Models","date":"2025-03-12","arxiv_id":"2503.09248","repositories_listed":0,"syntology":null},{"url":null,"slug":"mads-multi-attribute-document-supervision-for","title":"MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification","date":"2025-03-10","arxiv_id":"2503.06847","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01019","title":"MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations","date":"2025-03-02","arxiv_id":"2503.01019","repositories_listed":0,"syntology":null},{"url":null,"slug":"retaining-knowledge-and-enhancing-long-text","title":"Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-ping-boosting-lightweight-vision","title":"CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance","date":"2024-12-05","arxiv_id":"2412.03871","repositories_listed":0,"syntology":null},{"url":null,"slug":"tripletclip-improving-compositional-reasoning","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","date":"2024-11-04","arxiv_id":"2411.02545","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-enriched-zero-shot-image","title":"Retrieval-enriched zero-shot image classification in low-resource domains","date":"2024-11-01","arxiv_id":"2411.00988","repositories_listed":0,"syntology":null},{"url":null,"slug":"csa-data-efficient-mapping-of-unimodal","title":"CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features","date":"2024-10-10","arxiv_id":"2410.07610","repositories_listed":0,"syntology":null},{"url":null,"slug":"logra-med-long-context-multi-graph-alignment","title":"LoGra-Med: Long Context Multi-Graph Alignment for Medical Vision-Language Model","date":"2024-10-03","arxiv_id":"2410.02615","repositories_listed":0,"syntology":null},{"url":null,"slug":"coapt-context-attribute-words-for-prompt","title":"CoAPT: Context Attribute words for Prompt Tuning","date":"2024-07-18","arxiv_id":"2407.13808","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-compositions-enhance-vision-language","title":"Semantic Compositions Enhance Vision-Language Contrastive Learning","date":"2024-07-01","arxiv_id":"2407.01408","repositories_listed":0,"syntology":null},{"url":null,"slug":"bafta-backprop-free-test-time-adaptation-for","title":"BaFTA: Backprop-Free Test-Time Adaptation For Zero-Shot Vision-Language Models","date":"2024-06-17","arxiv_id":"2406.11309","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-many-to-many-relationships-for","title":"Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships","date":"2024-05-29","arxiv_id":"2405.18770","repositories_listed":0,"syntology":null},{"url":null,"slug":"its-not-a-modality-gap-characterizing-and","title":"It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap","date":"2024-05-28","arxiv_id":"2405.18570","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-method-integration-with-confidence","title":"Multi-method Integration with Confidence-based Weighting for Zero-shot Image Classification","date":"2024-05-03","arxiv_id":"2405.02155","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-progressive-framework-of-vision-language","title":"A Progressive Framework of Vision-language Knowledge Distillation and Alignment for Multilingual Scene","date":"2024-04-17","arxiv_id":"2404.11249","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridge-the-modality-and-capacity-gaps-in","title":"Bridge the Modality and Capability Gaps in Vision-Language Model Selection","date":"2024-03-20","arxiv_id":"2403.13797","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-low-resource-medical-image","title":"Exploring Low-Resource Medical Image Classification with Weakly Supervised Prompt Learning","date":"2024-02-06","arxiv_id":"2402.03783","repositories_listed":0,"syntology":null},{"url":null,"slug":"clamp-contrastive-language-model-prompt","title":"CLAMP: Contrastive LAnguage Model Prompt-tuning","date":"2023-12-04","arxiv_id":"2312.01629","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightclip-learning-multi-level-interaction","title":"LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models","date":"2023-12-01","arxiv_id":"2312.00674","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-model-agnostic-multi-group","title":"Efficient Model-Agnostic Multi-Group Equivariant Networks","date":"2023-10-14","arxiv_id":"2310.09675","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-tolerant-unsupervised-adapter-for","title":"Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language Models","date":"2023-09-26","arxiv_id":"2309.14928","repositories_listed":0,"syntology":null},{"url":null,"slug":"growclip-data-aware-automatic-model-growing","title":"GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training","date":"2023-08-22","arxiv_id":"2308.11331","repositories_listed":0,"syntology":null},{"url":null,"slug":"visually-grounded-descriptions-improve-zero","title":"Semantically-Prompted Language Models Improve Visual Descriptions","date":"2023-06-05","arxiv_id":"2306.06077","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-models-performing-zero-shot","title":"Vision-Language Models Performing Zero-Shot Tasks Exhibit Gender-based Disparities","date":"2023-01-26","arxiv_id":"2301.11100","repositories_listed":0,"syntology":null},{"url":null,"slug":"ra-clip-retrieval-augmented-contrastive","title":"RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dirac-i-identifying-diverse-and-rare-training","title":"DiRaC-I: Identifying Diverse and Rare Training Classes for Zero-Shot Learning","date":"2022-12-31","arxiv_id":"2301.00236","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-are-lemons-purple-the-concept","title":"When are Lemons Purple? The Concept Association Bias of Vision-Language Models","date":"2022-12-22","arxiv_id":"2212.12043","repositories_listed":0,"syntology":null},{"url":null,"slug":"i2mvformer-large-language-model-generated","title":"I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification","date":"2022-12-05","arxiv_id":"2212.02291","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-negative-text-replay-for-continual","title":"Generative Negative Text Replay for Continual Vision-Language Pretraining","date":"2022-10-31","arxiv_id":"2210.17322","repositories_listed":0,"syntology":null},{"url":null,"slug":"text2model-model-induction-for-zero-shot","title":"Text2Model: Text-based Model Induction for Zero-shot Image Classification","date":"2022-10-27","arxiv_id":"2210.15182","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-multilingual-multi-modal-pre","title":"Efficient Multilingual Multi-modal Pre-training through Triple Contrastive Loss","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"i2dformer-learning-image-to-document","title":"I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification","date":"2022-09-21","arxiv_id":"2209.10304","repositories_listed":0,"syntology":null},{"url":null,"slug":"pyramidclip-hierarchical-feature-alignment","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining","date":"2022-04-29","arxiv_id":"2204.14095","repositories_listed":0,"syntology":null}],"syntology_records":28,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_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_where_code_ran":25,"papers_where_code_ran_first_page":"/task/zero-shot-image-classification/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/zero-shot-image-classification/papers/2","json":"/task/zero-shot-image-classification/papers/2.json","rows":11},{"order":"ran","page":1,"of":1,"url":"/task/zero-shot-image-classification/papers/ran/1","json":"/task/zero-shot-image-classification/papers/ran/1.json","rows":25}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"6917049370f5a4c8907a2e8e7a9dad991447e01d8589d7183c0c921f2c52b95f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}