{"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/elevater","name":"ELEVATER","full_name":"Evaluation of Language-augmented Visual Task-level Transfer","description_markdown":"The ELEVATER benchmark is a collection of resources for training, evaluating, and analyzing language-image models on image classification and object detection. ELEVATER consists of:\r\n\r\n- Benchmark: A benchmark suite that consists of 20 image classification datasets and 35 object detection datasets, augmented with external knowledge\r\n- Toolkit: An automatic hyper-parameter tuning toolkit; Strong language-augmented efficient model adaptation methods.\r\n- Baseline: Pre-trained language-free and language-augmented visual models.\r\n- Knowledge: A platform to study the benefit of external knowledge for vision problems.\r\n- Evaluation Metrics: Sample-efficiency (zero-, few-, and full-shot) and Parameter-efficiency.\r\n- Leaderboard: A public leaderboard to track performance on the benchmark\r\n\r\nThe ultimate goal of ELEVATER is to drive research in the development of language-image models to tackle core computer vision problems in the wild.","description_withheld":null,"homepage":"https://computer-vision-in-the-wild.github.io/ELEVATER/","introduced_date":"2022-04-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/elevater-a-benchmark-and-toolkit-for","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","first_author":"Chunyuan Li","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Few-Shot Object Detection","url":"/task/few-shot-object-detection","datasets_with_task":"/datasets/task/few-shot-object-detection"},{"name":"Zero-Shot Object Detection","url":"/task/zero-shot-object-detection","datasets_with_task":"/datasets/task/zero-shot-object-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ELEVATER","ODinW Full-shot 35 Tasks"],"data_loaders":[],"num_papers_in_archive":25,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/object-detection-on-odinw-full-shot-35-tasks","task":"Object Detection","dataset_variant":"ODinW Full-shot 35 Tasks","rows":2,"metrics":["AP"],"first_row_in_archive_order":{"model":"Grounding DINO 1.5 Pro","paper":"/paper/grounding-dino-1-5-advance-the-edge-of-open","metrics":{"AP":"72.4"},"code_links":[{"title":"mit-han-lab/efficientvit","url":"https://github.com/mit-han-lab/efficientvit"},{"title":"idea-research/grounded-sam-2","url":"https://github.com/idea-research/grounded-sam-2"},{"title":"idea-research/grounding-dino-1.5-api","url":"https://github.com/idea-research/grounding-dino-1.5-api"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/object-detection-on-elevater","task":"Object Detection","dataset_variant":"ELEVATER","rows":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"GLIP-T","paper":"/paper/elevater-a-benchmark-and-toolkit-for","metrics":{"AP":"62.6"},"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"}]},"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":2,"of":2,"counts":{"papers_with_a_benchmark_row":2,"with_a_code_link":2,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":2,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/grounding-dino-1-5-advance-the-edge-of-open","slug":"grounding-dino-1-5-advance-the-edge-of-open","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","date":"2024-05-16","arxiv_id":"2405.10300","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["idea-research/grounding-dino-1.5-api"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/grounding-dino-1-5-advance-the-edge-of-open#ran","syntology_url":"https://syntology.ai/paper/2405.10300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10300"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":4,"samples_unverified":8,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/grounding-dino-1-5-advance-the-edge-of-open","slug":"grounding-dino-1-5-advance-the-edge-of-open","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","date":"2024-05-16","arxiv_id":"2405.10300","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["idea-research/grounding-dino-1.5-api"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/grounding-dino-1-5-advance-the-edge-of-open#ran","syntology_url":"https://syntology.ai/paper/2405.10300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10300"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":4,"samples_unverified":8,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/elevater/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/elevater/papers/ran/1","json":"/dataset/elevater/papers/ran/1.json","rows":2}],"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":2,"samples_harvested":22,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":4,"samples_unverified":9,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"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":"8d7a9879aca2d6f488520c6a818f9f7202bb26b9e0dda1f09415843e29995a42","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}