{"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/fine-grained-predicates-learning-for-scene","title":"Fine-Grained Predicates Learning for Scene Graph Generation","arxiv_id":"2204.02597","date":"2022-04-06","proceeding":"CVPR 2022 1","authors":["Xinyu Lyu","Lianli Gao","Yuyu Guo","Zhou Zhao","Hao Huang","Heng Tao Shen","Jingkuan Song"],"abstract":"The performance of current Scene Graph Generation models is severely hampered by some hard-to-distinguish predicates, e.g., \"woman-on/standing on/walking on-beach\" or \"woman-near/looking at/in front of-child\". While general SGG models are prone to predict head predicates and existing re-balancing strategies prefer tail categories, none of them can appropriately handle these hard-to-distinguish predicates. To tackle this issue, inspired by fine-grained image classification, which focuses on differentiating among hard-to-distinguish object classes, we propose a method named Fine-Grained Predicates Learning (FGPL) which aims at differentiating among hard-to-distinguish predicates for Scene Graph Generation task. Specifically, we first introduce a Predicate Lattice that helps SGG models to figure out fine-grained predicate pairs. Then, utilizing the Predicate Lattice, we propose a Category Discriminating Loss and an Entity Discriminating Loss, which both contribute to distinguishing fine-grained predicates while maintaining learned discriminatory power over recognizable ones. The proposed model-agnostic strategy significantly boosts the performances of three benchmark models (Transformer, VCTree, and Motif) by 22.8\\%, 24.1\\% and 21.7\\% of Mean Recall (mR@100) on the Predicate Classification sub-task, respectively. Our model also outperforms state-of-the-art methods by a large margin (i.e., 6.1\\%, 4.6\\%, and 3.2\\% of Mean Recall (mR@100)) on the Visual Genome dataset.","url_abs":"https://arxiv.org/abs/2204.02597v2","url_pdf":"https://arxiv.org/pdf/2204.02597v2.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":"fine-grained-predicates-learning-for-scene","repo_url":"https://github.com/xinyulyu/fgpl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"predicate-classification","task_name":"Predicate Classification"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.02597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02597"}},"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/xinyulyu/fgpl","reach":null}],"summary":{"ran":4,"ran_violates":1,"ran_fixture":2,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"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":10,"samples":[{"code_sha256_prefix":"51831c7bffebd292","entry":"Label_Smoothing_Regression","repo":"xinyulyu/fgpl","repo_kind":"official","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","file_url":"https://github.com/xinyulyu/fgpl/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"51831c7bffebd292"}},{"code_sha256_prefix":"2249d096c9f89ccd","entry":"MyCrossEntropyLoss","repo":"xinyulyu/fgpl","repo_kind":"official","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","file_url":"https://github.com/xinyulyu/fgpl/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2249d096c9f89ccd"}},{"code_sha256_prefix":"b33af276d20651f6","entry":"TripletLoss","repo":"xinyulyu/fgpl","repo_kind":"official","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","file_url":"https://github.com/xinyulyu/fgpl/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b33af276d20651f6"}},{"code_sha256_prefix":"5a1f8b1aa2cee093","entry":"TripletLoss_CB","repo":"xinyulyu/fgpl","repo_kind":"official","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","file_url":"https://github.com/xinyulyu/fgpl/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a1f8b1aa2cee093"}},{"code_sha256_prefix":"2dac2d9248237ad8","entry":"adj_laplacian","repo":"xinyulyu/fgpl","repo_kind":"official","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","file_url":"https://github.com/xinyulyu/fgpl/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2dac2d9248237ad8"}},{"code_sha256_prefix":"6cbf46794989b731","entry":"cat","repo":"xinyulyu/fgpl","repo_kind":"official","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","file_url":"https://github.com/xinyulyu/fgpl/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6cbf46794989b731"}},{"code_sha256_prefix":"52d56edd43f3dbf5","entry":"log_weighted_softmax","repo":"xinyulyu/fgpl","repo_kind":"official","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","file_url":"https://github.com/xinyulyu/fgpl/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52d56edd43f3dbf5"}},{"code_sha256_prefix":"0b1e1f4052f5c5e4","entry":"normalize","repo":"xinyulyu/fgpl","repo_kind":"official","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","file_url":"https://github.com/xinyulyu/fgpl/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0b1e1f4052f5c5e4"}},{"code_sha256_prefix":"de4f39fa50cb72f7","entry":"predicate_statistics","repo":"xinyulyu/fgpl","repo_kind":"official","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","file_url":"https://github.com/xinyulyu/fgpl/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"de4f39fa50cb72f7"}},{"code_sha256_prefix":"27df07933d843d50","entry":"RelationLossComputation","repo":"xinyulyu/fgpl","repo_kind":"official","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.py","file_url":"https://github.com/xinyulyu/fgpl/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/loss.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":"27df07933d843d50"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}