{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/vasr-visual-analogies-of-situation","title":"VASR: Visual Analogies of Situation Recognition","arxiv_id":"2212.04542","date":"2022-12-08","proceeding":null,"authors":["Yonatan Bitton","Ron Yosef","Eli Strugo","Dafna Shahaf","Roy Schwartz","Gabriel Stanovsky"],"abstract":"A core process in human cognition is analogical mapping: the ability to identify a similar relational structure between different situations. We introduce a novel task, Visual Analogies of Situation Recognition, adapting the classical word-analogy task into the visual domain. Given a triplet of images, the task is to select an image candidate B' that completes the analogy (A to A' is like B to what?). Unlike previous work on visual analogy that focused on simple image transformations, we tackle complex analogies requiring understanding of scenes. We leverage situation recognition annotations and the CLIP model to generate a large set of 500k candidate analogies. Crowdsourced annotations for a sample of the data indicate that humans agree with the dataset label ~80% of the time (chance level 25%). Furthermore, we use human annotations to create a gold-standard dataset of 3,820 validated analogies. Our experiments demonstrate that state-of-the-art models do well when distractors are chosen randomly (~86%), but struggle with carefully chosen distractors (~53%, compared to 90% human accuracy). We hope our dataset will encourage the development of new analogy-making models. Website: https://vasr-dataset.github.io/","url_abs":"https://arxiv.org/abs/2212.04542v1","url_pdf":"https://arxiv.org/pdf/2212.04542v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"vasr-visual-analogies-of-situation","repo_url":"https://github.com/vasr-dataset/vasr","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"visual-analogies","task_name":"Visual Analogies"},{"task_slug":"visual-commonsense-reasoning","task_name":"Visual Commonsense Reasoning"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[{"slug":"vasr","name":"VASR","full_name":"Visual Analogies of Situation Recognition"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-reasoning-on-vasr","task":"Visual Reasoning","dataset":"VASR","model":"Swin","rank_in_archive_order":1,"of":4,"metrics":{"1:1 Accuracy":"52.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-vasr","task":"Visual Reasoning","dataset":"VASR","model":"ConvNeXt","rank_in_archive_order":2,"of":4,"metrics":{"1:1 Accuracy":"51.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-vasr","task":"Visual Reasoning","dataset":"VASR","model":"ViT","rank_in_archive_order":3,"of":4,"metrics":{"1:1 Accuracy":"50.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-vasr","task":"Visual Reasoning","dataset":"VASR","model":"DEiT","rank_in_archive_order":4,"of":4,"metrics":{"1:1 Accuracy":"47.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.04542","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04542"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vasr-dataset/vasr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a9c309927ba2e283","entry":"calculate_accuracy","repo":"vasr-dataset/vasr","repo_kind":"official","path":"experiments/utils.py","file_url":"https://github.com/vasr-dataset/vasr/blob/HEAD/experiments/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9c309927ba2e283"}},{"code_sha256_prefix":"a09718f9096a1801","entry":"calculate_size_proportions","repo":"vasr-dataset/vasr","repo_kind":"official","path":"dataset/pipeline/C_filter_visual.py","file_url":"https://github.com/vasr-dataset/vasr/blob/HEAD/dataset/pipeline/C_filter_visual.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a09718f9096a1801"}},{"code_sha256_prefix":"8da4ede1807a6c92","entry":"count_intersecting_diff_key_AB","repo":"vasr-dataset/vasr","repo_kind":"official","path":"dataset/pipeline/A_find_AB_pairs.py","file_url":"https://github.com/vasr-dataset/vasr/blob/HEAD/dataset/pipeline/A_find_AB_pairs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8da4ede1807a6c92"}},{"code_sha256_prefix":"5b8a29188c340a69","entry":"dump_train_info","repo":"vasr-dataset/vasr","repo_kind":"official","path":"experiments/utils.py","file_url":"https://github.com/vasr-dataset/vasr/blob/HEAD/experiments/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b8a29188c340a69"}},{"code_sha256_prefix":"40605229814712da","entry":"filter_by_legit_pairs_and_sample","repo":"vasr-dataset/vasr","repo_kind":"official","path":"dataset/pipeline/B_filter_textual.py","file_url":"https://github.com/vasr-dataset/vasr/blob/HEAD/dataset/pipeline/B_filter_textual.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40605229814712da"}},{"code_sha256_prefix":"daadf88214823ae9","entry":"get_bbox_of_diff_item","repo":"vasr-dataset/vasr","repo_kind":"official","path":"dataset/pipeline/C_filter_visual.py","file_url":"https://github.com/vasr-dataset/vasr/blob/HEAD/dataset/pipeline/C_filter_visual.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"daadf88214823ae9"}},{"code_sha256_prefix":"8753077ca7bddb4c","entry":"run_trained_scores","repo":"vasr-dataset/vasr","repo_kind":"official","path":"experiments/run_zero_shot.py","file_url":"https://github.com/vasr-dataset/vasr/blob/HEAD/experiments/run_zero_shot.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8753077ca7bddb4c"}},{"code_sha256_prefix":"f93a5d6a3488c688","entry":"train_epoch","repo":"vasr-dataset/vasr","repo_kind":"official","path":"experiments/run_trainable.py","file_url":"https://github.com/vasr-dataset/vasr/blob/HEAD/experiments/run_trainable.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f93a5d6a3488c688"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}