{"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/pdiscoformer-relaxing-part-discovery","title":"PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers","arxiv_id":"2407.04538","date":"2024-07-05","proceeding":null,"authors":["Ananthu Aniraj","Cassio F. Dantas","Dino Ienco","Diego Marcos"],"abstract":"Computer vision methods that explicitly detect object parts and reason on them are a step towards inherently interpretable models. Existing approaches that perform part discovery driven by a fine-grained classification task make very restrictive assumptions on the geometric properties of the discovered parts; they should be small and compact. Although this prior is useful in some cases, in this paper we show that pre-trained transformer-based vision models, such as self-supervised DINOv2 ViT, enable the relaxation of these constraints. In particular, we find that a total variation (TV) prior, which allows for multiple connected components of any size, substantially outperforms previous work. We test our approach on three fine-grained classification benchmarks: CUB, PartImageNet and Oxford Flowers, and compare our results to previously published methods as well as a re-implementation of the state-of-the-art method PDiscoNet with a transformer-based backbone. We consistently obtain substantial improvements across the board, both on part discovery metrics and the downstream classification task, showing that the strong inductive biases in self-supervised ViT models require to rethink the geometric priors that can be used for unsupervised part discovery.","url_abs":"https://arxiv.org/abs/2407.04538v3","url_pdf":"https://arxiv.org/pdf/2407.04538v3.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":"pdiscoformer-relaxing-part-discovery","repo_url":"https://github.com/ananthu-aniraj/pdiscoformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"unsupervised-part-discovery","task_name":"Unsupervised Part Discovery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.04538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04538"}},"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/ananthu-aniraj/pdiscoformer","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"2255405dfa5c835b","entry":"get_dimensions","repo":"ananthu-aniraj/pdiscoformer","repo_kind":"official","path":"utils/data_utils/dataset_utils.py","file_url":"https://github.com/ananthu-aniraj/pdiscoformer/blob/HEAD/utils/data_utils/dataset_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2255405dfa5c835b"}},{"code_sha256_prefix":"cea473d993ab7c54","entry":"load_json","repo":"ananthu-aniraj/pdiscoformer","repo_kind":"official","path":"utils/data_utils/dataset_utils.py","file_url":"https://github.com/ananthu-aniraj/pdiscoformer/blob/HEAD/utils/data_utils/dataset_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cea473d993ab7c54"}},{"code_sha256_prefix":"6df2bbbda7469611","entry":"pil_loader","repo":"ananthu-aniraj/pdiscoformer","repo_kind":"official","path":"utils/data_utils/dataset_utils.py","file_url":"https://github.com/ananthu-aniraj/pdiscoformer/blob/HEAD/utils/data_utils/dataset_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6df2bbbda7469611"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}