{"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/sgtr-end-to-end-scene-graph-generation-with","title":"SGTR: End-to-end Scene Graph Generation with Transformer","arxiv_id":"2112.12970","date":"2021-12-24","proceeding":"CVPR 2022 1","authors":["Rongjie Li","Songyang Zhang","Xuming He"],"abstract":"Scene Graph Generation (SGG) remains a challenging visual understanding task due to its compositional property. Most previous works adopt a bottom-up two-stage or a point-based one-stage approach, which often suffers from high time complexity or sub-optimal designs. In this work, we propose a novel SGG method to address the aforementioned issues, formulating the task as a bipartite graph construction problem. To solve the problem, we develop a transformer-based end-to-end framework that first generates the entity and predicate proposal set, followed by inferring directed edges to form the relation triplets. In particular, we develop a new entity-aware predicate representation based on a structural predicate generator that leverages the compositional property of relationships. Moreover, we design a graph assembling module to infer the connectivity of the bipartite scene graph based on our entity-aware structure, enabling us to generate the scene graph in an end-to-end manner. Extensive experimental results show that our design is able to achieve the state-of-the-art or comparable performance on two challenging benchmarks, surpassing most of the existing approaches and enjoying higher efficiency in inference. We hope our model can serve as a strong baseline for the Transformer-based scene graph generation. Code is available: https://github.com/Scarecrow0/SGTR","url_abs":"https://arxiv.org/abs/2112.12970v3","url_pdf":"https://arxiv.org/pdf/2112.12970v3.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":"sgtr-end-to-end-scene-graph-generation-with","repo_url":"https://github.com/scarecrow0/sgtr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"},{"task_slug":"graph-construction","task_name":"graph construction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.12970","atlas_url":"https://app.syntology.ai/?focus=2112.12970","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.12970"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/scarecrow0/sgtr","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":7,"samples":[{"code_sha256_prefix":"e8526a516b4f9206","entry":"convert_basic_c2_names","repo":"scarecrow0/sgtr","repo_kind":"official","path":"cvpods/checkpoint/c2_model_loading.py","file_url":"https://github.com/scarecrow0/sgtr/blob/HEAD/cvpods/checkpoint/c2_model_loading.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e8526a516b4f9206"}},{"code_sha256_prefix":"bab85846ecb8afc2","entry":"convert_c2_detectron_names","repo":"scarecrow0/sgtr","repo_kind":"official","path":"cvpods/checkpoint/c2_model_loading.py","file_url":"https://github.com/scarecrow0/sgtr/blob/HEAD/cvpods/checkpoint/c2_model_loading.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"bab85846ecb8afc2"}},{"code_sha256_prefix":"d4480baa30059dcb","entry":"genertate_info_tree","repo":"scarecrow0/sgtr","repo_kind":"official","path":"cvpods/analyser/module_profiler.py","file_url":"https://github.com/scarecrow0/sgtr/blob/HEAD/cvpods/analyser/module_profiler.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d4480baa30059dcb"}},{"code_sha256_prefix":"49a8a6f43aaea42a","entry":"get_activation","repo":"scarecrow0/sgtr","repo_kind":"official","path":"cvpods/layers/batch_norm.py","file_url":"https://github.com/scarecrow0/sgtr/blob/HEAD/cvpods/layers/batch_norm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"49a8a6f43aaea42a"}},{"code_sha256_prefix":"83c03ceb1307c6c4","entry":"inverse_sigmoid","repo":"scarecrow0/sgtr","repo_kind":"official","path":"cvpods/layers/deformable_transformer.py","file_url":"https://github.com/scarecrow0/sgtr/blob/HEAD/cvpods/layers/deformable_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"83c03ceb1307c6c4"}},{"code_sha256_prefix":"48fee46824d04966","entry":"traces_to_display","repo":"scarecrow0/sgtr","repo_kind":"official","path":"cvpods/analyser/module_profiler.py","file_url":"https://github.com/scarecrow0/sgtr/blob/HEAD/cvpods/analyser/module_profiler.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"48fee46824d04966"}},{"code_sha256_prefix":"f5c486b4bfc7db37","entry":"align_and_update_state_dicts","repo":"scarecrow0/sgtr","repo_kind":"official","path":"cvpods/checkpoint/c2_model_loading.py","file_url":"https://github.com/scarecrow0/sgtr/blob/HEAD/cvpods/checkpoint/c2_model_loading.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f5c486b4bfc7db37"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}