{"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/visual-concepts-tokenization","title":"Visual Concepts Tokenization","arxiv_id":"2205.10093","date":"2022-05-20","proceeding":null,"authors":["Tao Yang","Yuwang Wang","Yan Lu","Nanning Zheng"],"abstract":"Obtaining the human-like perception ability of abstracting visual concepts from concrete pixels has always been a fundamental and important target in machine learning research fields such as disentangled representation learning and scene decomposition. Towards this goal, we propose an unsupervised transformer-based Visual Concepts Tokenization framework, dubbed VCT, to perceive an image into a set of disentangled visual concept tokens, with each concept token responding to one type of independent visual concept. Particularly, to obtain these concept tokens, we only use cross-attention to extract visual information from the image tokens layer by layer without self-attention between concept tokens, preventing information leakage across concept tokens. We further propose a Concept Disentangling Loss to facilitate that different concept tokens represent independent visual concepts. The cross-attention and disentangling loss play the role of induction and mutual exclusion for the concept tokens, respectively. Extensive experiments on several popular datasets verify the effectiveness of VCT on the tasks of disentangled representation learning and scene decomposition. VCT achieves the state of the art results by a large margin.","url_abs":"https://arxiv.org/abs/2205.10093v2","url_pdf":"https://arxiv.org/pdf/2205.10093v2.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":"visual-concepts-tokenization","repo_url":"https://github.com/thomasmry/vct","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"visual-concepts-tokenization","repo_url":"https://github.com/thomasmry/disdiff","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2205.10093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10093"}},"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/thomasmry/disdiff","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thomasmry/vct","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran_violates":2,"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":"8458f9ba0361ff43","entry":"cache_fn","repo":"ThomasMrY/VCT","repo_kind":"official","path":"models/visual_concept_tokenizor.py","file_url":"https://github.com/ThomasMrY/VCT/blob/HEAD/models/visual_concept_tokenizor.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":"8458f9ba0361ff43"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":"ThomasMrY/VCT","repo_kind":"official","path":"models/visual_concept_tokenizor.py","file_url":"https://github.com/ThomasMrY/VCT/blob/HEAD/models/visual_concept_tokenizor.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"ThomasMrY/VCT","repo_kind":"official","path":"models/visual_concept_tokenizor.py","file_url":"https://github.com/ThomasMrY/VCT/blob/HEAD/models/visual_concept_tokenizor.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"8d9799f635994e6a","entry":"gen_image","repo":"ThomasMrY/VCT","repo_kind":"official","path":"main_vct.py","file_url":"https://github.com/ThomasMrY/VCT/blob/HEAD/main_vct.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d9799f635994e6a"}},{"code_sha256_prefix":"10c5524b4176c7a5","entry":"return_shape","repo":"ThomasMrY/VCT","repo_kind":"official","path":"main_vct.py","file_url":"https://github.com/ThomasMrY/VCT/blob/HEAD/main_vct.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"10c5524b4176c7a5"}},{"code_sha256_prefix":"4781b61f9e2e5b4d","entry":"decode_image","repo":"ThomasMrY/VCT","repo_kind":"official","path":"main_vct.py","file_url":"https://github.com/ThomasMrY/VCT/blob/HEAD/main_vct.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":"4781b61f9e2e5b4d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}