{"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/fine-grained-scene-graph-generation-with-data","title":"Fine-Grained Scene Graph Generation with Data Transfer","arxiv_id":"2203.11654","date":"2022-03-22","proceeding":null,"authors":["Ao Zhang","Yuan YAO","Qianyu Chen","Wei Ji","Zhiyuan Liu","Maosong Sun","Tat-Seng Chua"],"abstract":"Scene graph generation (SGG) is designed to extract (subject, predicate, object) triplets in images. Recent works have made a steady progress on SGG, and provide useful tools for high-level vision and language understanding. However, due to the data distribution problems including long-tail distribution and semantic ambiguity, the predictions of current SGG models tend to collapse to several frequent but uninformative predicates (e.g., on, at), which limits practical application of these models in downstream tasks. To deal with the problems above, we propose a novel Internal and External Data Transfer (IETrans) method, which can be applied in a plug-and-play fashion and expanded to large SGG with 1,807 predicate classes. Our IETrans tries to relieve the data distribution problem by automatically creating an enhanced dataset that provides more sufficient and coherent annotations for all predicates. By training on the enhanced dataset, a Neural Motif model doubles the macro performance while maintaining competitive micro performance. The code and data are publicly available at https://github.com/waxnkw/IETrans-SGG.pytorch.","url_abs":"https://arxiv.org/abs/2203.11654v2","url_pdf":"https://arxiv.org/pdf/2203.11654v2.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-scene-graph-generation-with-data","repo_url":"https://github.com/waxnkw/ietrans-sgg.pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"fine-grained-scene-graph-generation-with-data","repo_url":"https://github.com/rlqja1107/torch-st-sgg","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":"predicate-classification","task_name":"Predicate Classification"},{"task_slug":"scene-graph-classification","task_name":"Scene Graph Classification"},{"task_slug":"scene-graph-detection","task_name":"Scene Graph Detection"},{"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/scene-graph-generation-on-visual-genome","task":"Scene Graph Generation","dataset":"Visual Genome","model":"IETrans","rank_in_archive_order":11,"of":19,"metrics":{"Recall@100":"27.2","Recall@50":"23.5","mean Recall @100":"18.0"},"uses_additional_data":false},{"leaderboard":"/sota/unbiased-scene-graph-generation-on-visual","task":"Unbiased Scene Graph Generation","dataset":"Visual Genome","model":"IETrans (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode)","rank_in_archive_order":1,"of":31,"metrics":{"F@100":"44.1","mR@20":"28.9","ng-mR@20":"36.0"},"uses_additional_data":false},{"leaderboard":"/sota/unbiased-scene-graph-generation-on-visual","task":"Unbiased Scene Graph Generation","dataset":"Visual Genome","model":"IETrans (MOTIFS-ResNeXt-101-FPN backbone; SGCls mode)","rank_in_archive_order":7,"of":31,"metrics":{"F@100":"26.0","mR@20":"17.5","ng-mR@20":"21.8"},"uses_additional_data":false},{"leaderboard":"/sota/unbiased-scene-graph-generation-on-visual","task":"Unbiased Scene Graph Generation","dataset":"Visual Genome","model":"IETrans (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode)","rank_in_archive_order":14,"of":31,"metrics":{"F@100":"21.7","mR@20":"10.9","ng-mR@20":"13.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.11654","atlas_url":"https://app.syntology.ai/?focus=2203.11654","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":"2203.11654"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2203.11654\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2203.11654"},"call":"get_concepts_for_paper(arxiv_id=\"2203.11654\")"}],"by_repo":[{"repo":"waxnkw/ietrans-sgg.pytorch","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rlqja1107/torch-st-sgg","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2401.09786"],"harvested_for_calls":[{"arxiv_id":"2401.09786","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2401.09786"},"call":"get_harvested_code_for_paper(arxiv_id=\"2401.09786\")"}]}],"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":"4c5c278a663082fe96450a71a54f65036bd0b38f22b71768d5fcd353cbda6059","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}