{"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/object-centric-learning-with-cyclic-walks-1","title":"Object-centric Learning with Cyclic Walks between Parts and Whole","arxiv_id":"2302.08023","date":"2023-02-16","proceeding":"NeurIPS 2023 11","authors":["Ziyu Wang","Mike Zheng Shou","Mengmi Zhang"],"abstract":"Learning object-centric representations from complex natural environments enables both humans and machines with reasoning abilities from low-level perceptual features. To capture compositional entities of the scene, we proposed cyclic walks between perceptual features extracted from vision transformers and object entities. First, a slot-attention module interfaces with these perceptual features and produces a finite set of slot representations. These slots can bind to any object entities in the scene via inter-slot competitions for attention. Next, we establish entity-feature correspondence with cyclic walks along high transition probability based on the pairwise similarity between perceptual features (aka \"parts\") and slot-binded object representations (aka \"whole\"). The whole is greater than its parts and the parts constitute the whole. The part-whole interactions form cycle consistencies, as supervisory signals, to train the slot-attention module. Our rigorous experiments on \\textit{seven} image datasets in \\textit{three} \\textit{unsupervised} tasks demonstrate that the networks trained with our cyclic walks can disentangle foregrounds and backgrounds, discover objects, and segment semantic objects in complex scenes. In contrast to object-centric models attached with a decoder for the pixel-level or feature-level reconstructions, our cyclic walks provide strong learning signals, avoiding computation overheads and enhancing memory efficiency. Our source code and data are available at: \\href{https://github.com/ZhangLab-DeepNeuroCogLab/Parts-Whole-Object-Centric-Learning/}{link}.","url_abs":"https://arxiv.org/abs/2302.08023v2","url_pdf":"https://arxiv.org/pdf/2302.08023v2.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":"object-centric-learning-with-cyclic-walks-1","repo_url":"https://github.com/zhanglab-deepneurocoglab/parts-whole-object-centric-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.08023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08023"}},"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/zhanglab-deepneurocoglab/parts-whole-object-centric-learning","reach":null}],"summary":{"ran":2,"ran_draft_wrong":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"b3bc34c7d153487b","entry":"SlotAttention","repo":"zhanglab-deepneurocoglab/parts-whole-object-centric-learning","repo_kind":"official","path":"models/sacrw.py","file_url":"https://github.com/zhanglab-deepneurocoglab/parts-whole-object-centric-learning/blob/HEAD/models/sacrw.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b3bc34c7d153487b"}},{"code_sha256_prefix":"59aabdc1922eaa50","entry":"SlotAttentionEncoder","repo":"zhanglab-deepneurocoglab/parts-whole-object-centric-learning","repo_kind":"official","path":"models/sacrw.py","file_url":"https://github.com/zhanglab-deepneurocoglab/parts-whole-object-centric-learning/blob/HEAD/models/sacrw.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"59aabdc1922eaa50"}},{"code_sha256_prefix":"1887705fac4b6be2","entry":"gru_cell","repo":"zhanglab-deepneurocoglab/parts-whole-object-centric-learning","repo_kind":"official","path":"models/sacrw.py","file_url":"https://github.com/zhanglab-deepneurocoglab/parts-whole-object-centric-learning/blob/HEAD/models/sacrw.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1887705fac4b6be2"}},{"code_sha256_prefix":"ce03601bb15eb7b0","entry":"linear","repo":"zhanglab-deepneurocoglab/parts-whole-object-centric-learning","repo_kind":"official","path":"models/sacrw.py","file_url":"https://github.com/zhanglab-deepneurocoglab/parts-whole-object-centric-learning/blob/HEAD/models/sacrw.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ce03601bb15eb7b0"}},{"code_sha256_prefix":"2744d74f0a6e7e72","entry":"positionalencoding2d","repo":"zhanglab-deepneurocoglab/parts-whole-object-centric-learning","repo_kind":"official","path":"models/sacrw.py","file_url":"https://github.com/zhanglab-deepneurocoglab/parts-whole-object-centric-learning/blob/HEAD/models/sacrw.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2744d74f0a6e7e72"}},{"code_sha256_prefix":"d769eb01f609340f","entry":"SACRW","repo":"zhanglab-deepneurocoglab/parts-whole-object-centric-learning","repo_kind":"official","path":"models/sacrw.py","file_url":"https://github.com/zhanglab-deepneurocoglab/parts-whole-object-centric-learning/blob/HEAD/models/sacrw.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d769eb01f609340f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}