{"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/transformer-based-dual-relation-graph-for-1","title":"Transformer-based Dual Relation Graph for Multi-label Image Recognition","arxiv_id":"2110.04722","date":"2021-10-10","proceeding":"ICCV 2021 10","authors":["Jiawei Zhao","Ke Yan","Yifan Zhao","Xiaowei Guo","Feiyue Huang","Jia Li"],"abstract":"The simultaneous recognition of multiple objects in one image remains a challenging task, spanning multiple events in the recognition field such as various object scales, inconsistent appearances, and confused inter-class relationships. Recent research efforts mainly resort to the statistic label co-occurrences and linguistic word embedding to enhance the unclear semantics. Different from these researches, in this paper, we propose a novel Transformer-based Dual Relation learning framework, constructing complementary relationships by exploring two aspects of correlation, i.e., structural relation graph and semantic relation graph. The structural relation graph aims to capture long-range correlations from object context, by developing a cross-scale transformer-based architecture. The semantic graph dynamically models the semantic meanings of image objects with explicit semantic-aware constraints. In addition, we also incorporate the learnt structural relationship into the semantic graph, constructing a joint relation graph for robust representations. With the collaborative learning of these two effective relation graphs, our approach achieves new state-of-the-art on two popular multi-label recognition benchmarks, i.e., MS-COCO and VOC 2007 dataset.","url_abs":"https://arxiv.org/abs/2110.04722v2","url_pdf":"https://arxiv.org/pdf/2110.04722v2.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":"transformer-based-dual-relation-graph-for-1","repo_url":"https://github.com/iCVTEAM/TDRG","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"multi-label-image-recognition","task_name":"Multi-Label Image Recognition"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-label-classification-on-ms-coco","task":"Multi-Label Classification","dataset":"MS-COCO","model":"TDRG-R101(576×576)","rank_in_archive_order":22,"of":34,"metrics":{"mAP":"86.0"},"uses_additional_data":false},{"leaderboard":"/sota/multi-label-classification-on-ms-coco","task":"Multi-Label Classification","dataset":"MS-COCO","model":"TDRG-R101(448×448)","rank_in_archive_order":26,"of":34,"metrics":{"mAP":"84.6"},"uses_additional_data":false},{"leaderboard":"/sota/multi-label-classification-on-pascal-voc-2007","task":"Multi-Label Classification","dataset":"PASCAL VOC 2007","model":"TDRG-R101(448×448)","rank_in_archive_order":10,"of":17,"metrics":{"mAP":"95.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.04722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04722"}},"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/iCVTEAM/TDRG","reach":null}],"summary":{"ran":8,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":12,"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":0,"samples":[{"code_sha256_prefix":"4af7cba6f2b6a00b","entry":"GraphConvolution","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4af7cba6f2b6a00b"}},{"code_sha256_prefix":"0fdd4b27f23fb10e","entry":"PositionEmbeddingLearned","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0fdd4b27f23fb10e"}},{"code_sha256_prefix":"19ad134c39cefe3a","entry":"PositionEmbeddingSine","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"19ad134c39cefe3a"}},{"code_sha256_prefix":"b98e254770325b03","entry":"TopKMaxPooling","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b98e254770325b03"}},{"code_sha256_prefix":"e3629529c763edf7","entry":"TransformerDecoder","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e3629529c763edf7"}},{"code_sha256_prefix":"a1044a3d81853ba9","entry":"TransformerDecoderLayer","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a1044a3d81853ba9"}},{"code_sha256_prefix":"8ee0966a4a5305fa","entry":"TransformerEncoder","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ee0966a4a5305fa"}},{"code_sha256_prefix":"4a32b2ac8f43376e","entry":"TransformerEncoderLayer","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4a32b2ac8f43376e"}},{"code_sha256_prefix":"626421743e751cfd","entry":"build_position_encoding","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"626421743e751cfd"}},{"code_sha256_prefix":"e32b7a1a6935ef81","entry":"TDRG","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e32b7a1a6935ef81"}},{"code_sha256_prefix":"a6af96a295df827c","entry":"Transformer","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6af96a295df827c"}},{"code_sha256_prefix":"2a6ad2bf42c596fb","entry":"build_transformer","repo":"iCVTEAM/TDRG","repo_kind":"official","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2a6ad2bf42c596fb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}