{"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/vision-relation-transformer-for-unbiased","title":"Vision Relation Transformer for Unbiased Scene Graph Generation","arxiv_id":"2308.09472","date":"2023-08-18","proceeding":"ICCV 2023 1","authors":["Gopika Sudhakaran","Devendra Singh Dhami","Kristian Kersting","Stefan Roth"],"abstract":"Recent years have seen a growing interest in Scene Graph Generation (SGG), a comprehensive visual scene understanding task that aims to predict entity relationships using a relation encoder-decoder pipeline stacked on top of an object encoder-decoder backbone. Unfortunately, current SGG methods suffer from an information loss regarding the entities local-level cues during the relation encoding process. To mitigate this, we introduce the Vision rElation TransfOrmer (VETO), consisting of a novel local-level entity relation encoder. We further observe that many existing SGG methods claim to be unbiased, but are still biased towards either head or tail classes. To overcome this bias, we introduce a Mutually Exclusive ExperT (MEET) learning strategy that captures important relation features without bias towards head or tail classes. Experimental results on the VG and GQA datasets demonstrate that VETO + MEET boosts the predictive performance by up to 47 percentage over the state of the art while being 10 times smaller.","url_abs":"https://arxiv.org/abs/2308.09472v1","url_pdf":"https://arxiv.org/pdf/2308.09472v1.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":"vision-relation-transformer-for-unbiased","repo_url":"https://github.com/visinf/veto","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"unbiased-scene-graph-generation","task_name":"Unbiased Scene Graph Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.09472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09472"}},"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":"deterministic:regex_extraction","url":"https://github.com/visinf/veto","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"a7dd305afad6384a","entry":"KL_divergence","repo":"visinf/veto","repo_kind":"official","path":"SHA_GCL_extra/kl_divergence.py","file_url":"https://github.com/visinf/veto/blob/HEAD/SHA_GCL_extra/kl_divergence.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":"a7dd305afad6384a"}},{"code_sha256_prefix":"34e6a1c47d6e4439","entry":"generate_current_predicate_set","repo":"visinf/veto","repo_kind":"official","path":"SHA_GCL_extra/extra_function_utils.py","file_url":"https://github.com/visinf/veto/blob/HEAD/SHA_GCL_extra/extra_function_utils.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":"34e6a1c47d6e4439"}},{"code_sha256_prefix":"10d0263db1bc534b","entry":"generate_num_stage_vector","repo":"visinf/veto","repo_kind":"official","path":"SHA_GCL_extra/extra_function_utils.py","file_url":"https://github.com/visinf/veto/blob/HEAD/SHA_GCL_extra/extra_function_utils.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":"10d0263db1bc534b"}},{"code_sha256_prefix":"999142f552583932","entry":"get_current_predicate_idx","repo":"visinf/veto","repo_kind":"official","path":"SHA_GCL_extra/extra_function_utils.py","file_url":"https://github.com/visinf/veto/blob/HEAD/SHA_GCL_extra/extra_function_utils.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":"999142f552583932"}},{"code_sha256_prefix":"e6b9d8bd426c698b","entry":"get_group_splits","repo":"visinf/veto","repo_kind":"official","path":"SHA_GCL_extra/group_chosen_function.py","file_url":"https://github.com/visinf/veto/blob/HEAD/SHA_GCL_extra/group_chosen_function.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":"e6b9d8bd426c698b"}},{"code_sha256_prefix":"2d943c0c96e61f16","entry":"entropy_loss","repo":"visinf/veto","repo_kind":"official","path":"pysgg/layers/entropy_loss.py","file_url":"https://github.com/visinf/veto/blob/HEAD/pysgg/layers/entropy_loss.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":true,"mcp_get_code":{"code_sha256":"2d943c0c96e61f16"}},{"code_sha256_prefix":"382942f3ada73679","entry":"kl_div_loss","repo":"visinf/veto","repo_kind":"official","path":"pysgg/layers/kl_div_loss.py","file_url":"https://github.com/visinf/veto/blob/HEAD/pysgg/layers/kl_div_loss.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":true,"mcp_get_code":{"code_sha256":"382942f3ada73679"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}