{"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/visual-commonsense-in-pretrained-unimodal-and-1","title":"Visual Commonsense in Pretrained Unimodal and Multimodal Models","arxiv_id":"2205.01850","date":"2022-05-04","proceeding":"NAACL 2022 7","authors":["Chenyu Zhang","Benjamin Van Durme","Zhuowan Li","Elias Stengel-Eskin"],"abstract":"Our commonsense knowledge about objects includes their typical visual attributes; we know that bananas are typically yellow or green, and not purple. Text and image corpora, being subject to reporting bias, represent this world-knowledge to varying degrees of faithfulness. In this paper, we investigate to what degree unimodal (language-only) and multimodal (image and language) models capture a broad range of visually salient attributes. To that end, we create the Visual Commonsense Tests (ViComTe) dataset covering 5 property types (color, shape, material, size, and visual co-occurrence) for over 5000 subjects. We validate this dataset by showing that our grounded color data correlates much better than ungrounded text-only data with crowdsourced color judgments provided by Paik et al. (2021). We then use our dataset to evaluate pretrained unimodal models and multimodal models. Our results indicate that multimodal models better reconstruct attribute distributions, but are still subject to reporting bias. Moreover, increasing model size does not enhance performance, suggesting that the key to visual commonsense lies in the data.","url_abs":"https://arxiv.org/abs/2205.01850v1","url_pdf":"https://arxiv.org/pdf/2205.01850v1.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":"visual-commonsense-in-pretrained-unimodal-and-1","repo_url":"https://github.com/chenyuheidizhang/vl-commonsense","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"visual-commonsense-tests","task_name":"Visual Commonsense Tests"},{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-commonsense-tests-on-vicomte-color","task":"Visual Commonsense Tests","dataset":"ViComTe-color","model":"BERT-large","rank_in_archive_order":1,"of":2,"metrics":{"Spearman's Rho":"37.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2205.01850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01850"}},"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/chenyuheidizhang/vl-commonsense","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":1,"ran_honours":2,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":6,"samples":[{"code_sha256_prefix":"d9eec16c0e1754f7","entry":"get_model_dist","repo":"chenyuheidizhang/vl-commonsense","repo_kind":"official","path":"probing/eval_zero_shot.py","file_url":"https://github.com/chenyuheidizhang/vl-commonsense/blob/HEAD/probing/eval_zero_shot.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d9eec16c0e1754f7"}},{"code_sha256_prefix":"6128da11044840b7","entry":"get_model_dist","repo":"chenyuheidizhang/vl-commonsense","repo_kind":"official","path":"soft-prompts/soft_prompts/run/model_eval.py","file_url":"https://github.com/chenyuheidizhang/vl-commonsense/blob/HEAD/soft-prompts/soft_prompts/run/model_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6128da11044840b7"}},{"code_sha256_prefix":"0e408186ad84c71b","entry":"get_token_ids","repo":"chenyuheidizhang/vl-commonsense","repo_kind":"official","path":"probing/eval_zero_shot.py","file_url":"https://github.com/chenyuheidizhang/vl-commonsense/blob/HEAD/probing/eval_zero_shot.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e408186ad84c71b"}},{"code_sha256_prefix":"58f0f0bbf7a9bcb1","entry":"get_token_ids","repo":"chenyuheidizhang/vl-commonsense","repo_kind":"official","path":"soft-prompts/soft_prompts/run/model_eval.py","file_url":"https://github.com/chenyuheidizhang/vl-commonsense/blob/HEAD/soft-prompts/soft_prompts/run/model_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"58f0f0bbf7a9bcb1"}},{"code_sha256_prefix":"4ad823467383d04e","entry":"get_log_probs","repo":"chenyuheidizhang/vl-commonsense","repo_kind":"official","path":"probing/eval_zero_shot.py","file_url":"https://github.com/chenyuheidizhang/vl-commonsense/blob/HEAD/probing/eval_zero_shot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4ad823467383d04e"}},{"code_sha256_prefix":"3f591af501d2eaac","entry":"load_obj_file","repo":"chenyuheidizhang/vl-commonsense","repo_kind":"official","path":"soft-prompts/soft_prompts/run/model_eval.py","file_url":"https://github.com/chenyuheidizhang/vl-commonsense/blob/HEAD/soft-prompts/soft_prompts/run/model_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3f591af501d2eaac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}