{"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/prototype-based-embedding-network-for-scene","title":"Prototype-based Embedding Network for Scene Graph Generation","arxiv_id":"2303.07096","date":"2023-03-13","proceeding":"CVPR 2023 1","authors":["Chaofan Zheng","Xinyu Lyu","Lianli Gao","Bo Dai","Jingkuan Song"],"abstract":"Current Scene Graph Generation (SGG) methods explore contextual information to predict relationships among entity pairs. However, due to the diverse visual appearance of numerous possible subject-object combinations, there is a large intra-class variation within each predicate category, e.g., \"man-eating-pizza, giraffe-eating-leaf\", and the severe inter-class similarity between different classes, e.g., \"man-holding-plate, man-eating-pizza\", in model's latent space. The above challenges prevent current SGG methods from acquiring robust features for reliable relation prediction. In this paper, we claim that the predicate's category-inherent semantics can serve as class-wise prototypes in the semantic space for relieving the challenges. To the end, we propose the Prototype-based Embedding Network (PE-Net), which models entities/predicates with prototype-aligned compact and distinctive representations and thereby establishes matching between entity pairs and predicates in a common embedding space for relation recognition. Moreover, Prototype-guided Learning (PL) is introduced to help PE-Net efficiently learn such entitypredicate matching, and Prototype Regularization (PR) is devised to relieve the ambiguous entity-predicate matching caused by the predicate's semantic overlap. Extensive experiments demonstrate that our method gains superior relation recognition capability on SGG, achieving new state-of-the-art performances on both Visual Genome and Open Images datasets.","url_abs":"https://arxiv.org/abs/2303.07096v1","url_pdf":"https://arxiv.org/pdf/2303.07096v1.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":"prototype-based-embedding-network-for-scene","repo_url":"https://github.com/vl-group/penet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-prediction","task_name":"Relation Prediction"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.07096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.07096"}},"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/vl-group/penet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/VL-Group/PENET","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"2d943c0c96e61f16","entry":"entropy_loss","repo":"VL-Group/PENET","repo_kind":"official","path":"maskrcnn_benchmark/layers/entropy_loss.py","file_url":"https://github.com/VL-Group/PENET/blob/HEAD/maskrcnn_benchmark/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":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"2d943c0c96e61f16"}},{"code_sha256_prefix":"2902bf4410253ff7","entry":"interpolate","repo":"VL-Group/PENET","repo_kind":"official","path":"maskrcnn_benchmark/layers/misc.py","file_url":"https://github.com/VL-Group/PENET/blob/HEAD/maskrcnn_benchmark/layers/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"2902bf4410253ff7"}},{"code_sha256_prefix":"382942f3ada73679","entry":"kl_div_loss","repo":"VL-Group/PENET","repo_kind":"official","path":"maskrcnn_benchmark/layers/kl_div_loss.py","file_url":"https://github.com/VL-Group/PENET/blob/HEAD/maskrcnn_benchmark/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":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"382942f3ada73679"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}