{"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/learning-visual-commonsense-for-robust-scene","title":"Learning Visual Commonsense for Robust Scene Graph Generation","arxiv_id":"2006.09623","date":"2020-06-17","proceeding":"ECCV 2020 8","authors":["Alireza Zareian","Zhecan Wang","Haoxuan You","Shih-Fu Chang"],"abstract":"Scene graph generation models understand the scene through object and predicate recognition, but are prone to mistakes due to the challenges of perception in the wild. Perception errors often lead to nonsensical compositions in the output scene graph, which do not follow real-world rules and patterns, and can be corrected using commonsense knowledge. We propose the first method to acquire visual commonsense such as affordance and intuitive physics automatically from data, and use that to improve the robustness of scene understanding. To this end, we extend Transformer models to incorporate the structure of scene graphs, and train our Global-Local Attention Transformer on a scene graph corpus. Once trained, our model can be applied on any scene graph generation model and correct its obvious mistakes, resulting in more semantically plausible scene graphs. Through extensive experiments, we show our model learns commonsense better than any alternative, and improves the accuracy of state-of-the-art scene graph generation methods.","url_abs":"https://arxiv.org/abs/2006.09623v2","url_pdf":"https://arxiv.org/pdf/2006.09623v2.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":"learning-visual-commonsense-for-robust-scene","repo_url":"https://github.com/ZhecanJamesWang/GLAT_SGG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-visual-commonsense-for-robust-scene","repo_url":"https://github.com/ZhecanJamesWang/GLAT_Visual_Commonsense","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-local-attention","method_name":"Global-Local Attention"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.09623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.09623"}},"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/ZhecanJamesWang/GLAT_SGG","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZhecanJamesWang/GLAT_Visual_Commonsense","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":8},"by_repo_kind":{"listed":{"samples":11,"ran":3,"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":"6c8dc09d0a783306","entry":"filter_dets","repo":"ZhecanJamesWang/GLAT_SGG","repo_kind":"listed","path":"lib/surgery.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/lib/surgery.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c8dc09d0a783306"}},{"code_sha256_prefix":"a1e587129dd2dfaf","entry":"get_ranking","repo":"ZhecanJamesWang/GLAT_SGG","repo_kind":"listed","path":"lib/pytorch_misc.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/lib/pytorch_misc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1e587129dd2dfaf"}},{"code_sha256_prefix":"fef49730c9e9a2b8","entry":"pairwise","repo":"ZhecanJamesWang/GLAT_SGG","repo_kind":"listed","path":"lib/pytorch_misc.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/lib/pytorch_misc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fef49730c9e9a2b8"}},{"code_sha256_prefix":"013f03d1624b019d","entry":"gather_res","repo":"ZhecanJamesWang/GLAT_SGG","repo_kind":"listed","path":"lib/object_detector.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/lib/object_detector.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":"013f03d1624b019d"}},{"code_sha256_prefix":"6f18f207a73aa64a","entry":"get_attn_key_pad_mask","repo":"ZhecanJamesWang/GLAT_SGG","repo_kind":"listed","path":"lib/models_kern.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/lib/models_kern.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":"6f18f207a73aa64a"}},{"code_sha256_prefix":"390a257a821b762d","entry":"get_non_pad_mask","repo":"ZhecanJamesWang/GLAT_SGG","repo_kind":"listed","path":"lib/models_kern.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/lib/models_kern.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":"390a257a821b762d"}},{"code_sha256_prefix":"6d0daf87a6ec7e39","entry":"optimistic_restore","repo":"ZhecanJamesWang/GLAT_SGG","repo_kind":"listed","path":"lib/pytorch_misc.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/lib/pytorch_misc.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":"6d0daf87a6ec7e39"}},{"code_sha256_prefix":"a2fca8a84cec8b3f","entry":"path","repo":"ZhecanJamesWang/GLAT_SGG","repo_kind":"listed","path":"config.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/config.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":"a2fca8a84cec8b3f"}},{"code_sha256_prefix":"9178ea1334f34247","entry":"split","repo":"ZhecanJamesWang/GLAT_SGG","repo_kind":"listed","path":"lib/models_kern.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/lib/models_kern.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":"9178ea1334f34247"}},{"code_sha256_prefix":"b907d8082fdf6836","entry":"stanford_path","repo":"ZhecanJamesWang/GLAT_SGG","repo_kind":"listed","path":"config.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/config.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":"b907d8082fdf6836"}},{"code_sha256_prefix":"16d7f949c9b0c390","entry":"vgg_fc","repo":"ZhecanJamesWang/GLAT_SGG","repo_kind":"listed","path":"lib/resnet.py","file_url":"https://github.com/ZhecanJamesWang/GLAT_SGG/blob/HEAD/lib/resnet.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":"16d7f949c9b0c390"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}