{"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":"/paper/pcpl-predicate-correlation-perception","title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","arxiv_id":"2009.00893","date":"2020-09-02","proceeding":null,"authors":["Shaotian Yan","Chen Shen","Zhongming Jin","Jianqiang Huang","Rongxin Jiang","Yaowu Chen","Xian-Sheng Hua"],"abstract":"Today, scene graph generation(SGG) task is largely limited in realistic scenarios, mainly due to the extremely long-tailed bias of predicate annotation distribution. Thus, tackling the class imbalance trouble of SGG is critical and challenging. In this paper, we first discover that when predicate labels have strong correlation with each other, prevalent re-balancing strategies(e.g., re-sampling and re-weighting) will give rise to either over-fitting the tail data(e.g., bench sitting on sidewalk rather than on), or still suffering the adverse effect from the original uneven distribution(e.g., aggregating varied parked on/standing on/sitting on into on). We argue the principal reason is that re-balancing strategies are sensitive to the frequencies of predicates yet blind to their relatedness, which may play a more important role to promote the learning of predicate features. Therefore, we propose a novel Predicate-Correlation Perception Learning(PCPL for short) scheme to adaptively seek out appropriate loss weights by directly perceiving and utilizing the correlation among predicate classes. Moreover, our PCPL framework is further equipped with a graph encoder module to better extract context features. Extensive experiments on the benchmark VG150 dataset show that the proposed PCPL performs markedly better on tail classes while well-preserving the performance on head ones, which significantly outperforms previous state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2009.00893v1","url_pdf":"https://arxiv.org/pdf/2009.00893v1.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":"pcpl-predicate-correlation-perception","repo_url":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"},{"task_slug":"unbiased-scene-graph-generation","task_name":"Unbiased Scene Graph Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unbiased-scene-graph-generation-on-visual","task":"Unbiased Scene Graph Generation","dataset":"Visual Genome","model":"PCPL (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode)","rank_in_archive_order":5,"of":31,"metrics":{"F@100":"35.7","mR@20":"19.3","ng-mR@20":"25.6"},"uses_additional_data":false},{"leaderboard":"/sota/unbiased-scene-graph-generation-on-visual","task":"Unbiased Scene Graph Generation","dataset":"Visual Genome","model":"PCPL (VCTree-ResNeXt-101-FPN backbone; PredCls mode)","rank_in_archive_order":6,"of":31,"metrics":{"F@100":"34.6","mR@20":"18.7","ng-mR@20":"25.1"},"uses_additional_data":false},{"leaderboard":"/sota/unbiased-scene-graph-generation-on-visual","task":"Unbiased Scene Graph Generation","dataset":"Visual Genome","model":"PCPL (VCTree-ResNeXt-101-FPN backbone; SGCls mode)","rank_in_archive_order":13,"of":31,"metrics":{"F@100":"23.2","mR@20":"12.7","ng-mR@20":"17.2"},"uses_additional_data":false},{"leaderboard":"/sota/unbiased-scene-graph-generation-on-visual","task":"Unbiased Scene Graph Generation","dataset":"Visual Genome","model":"PCPL (MOTIFS-ResNeXt-101-FPN backbone; SGCls mode)","rank_in_archive_order":15,"of":31,"metrics":{"F@100":"18.8","mR@20":"9.9","ng-mR@20":"13.1"},"uses_additional_data":false},{"leaderboard":"/sota/unbiased-scene-graph-generation-on-visual","task":"Unbiased Scene Graph Generation","dataset":"Visual Genome","model":"PCPL (VCTree-ResNeXt-101-FPN backbone; SGDet mode)","rank_in_archive_order":21,"of":31,"metrics":{"F@100":"17.8","mR@20":"8.1","ng-mR@20":"9.9"},"uses_additional_data":false},{"leaderboard":"/sota/unbiased-scene-graph-generation-on-visual","task":"Unbiased Scene Graph Generation","dataset":"Visual Genome","model":"PCPL (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode)","rank_in_archive_order":22,"of":31,"metrics":{"F@100":"18.0","mR@20":"8.0","ng-mR@20":"9.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.00893","atlas_url":"https://app.syntology.ai/?focus=2009.00893","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2009.00893"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2009.00893\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2009.00893"},"call":"get_concepts_for_paper(arxiv_id=\"2009.00893\")"}],"by_repo":[{"repo":"coldmanck/recovering-unbiased-scene-graphs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2002.11949"],"harvested_for_calls":[{"arxiv_id":"2002.11949","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2002.11949"},"call":"get_harvested_code_for_paper(arxiv_id=\"2002.11949\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"488fbcf61560143423ac9796c43bed98142adc0390442c6157b2ac5b589d1243","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}