{"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/probabilistic-conceptual-explainers","title":"Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models","arxiv_id":"2406.12649","date":"2024-06-18","proceeding":null,"authors":["Hengyi Wang","Shiwei Tan","Hao Wang"],"abstract":"Vision transformers (ViTs) have emerged as a significant area of focus, particularly for their capacity to be jointly trained with large language models and to serve as robust vision foundation models. Yet, the development of trustworthy explanation methods for ViTs has lagged, particularly in the context of post-hoc interpretations of ViT predictions. Existing sub-image selection approaches, such as feature-attribution and conceptual models, fall short in this regard. This paper proposes five desiderata for explaining ViTs -- faithfulness, stability, sparsity, multi-level structure, and parsimony -- and demonstrates the inadequacy of current methods in meeting these criteria comprehensively. We introduce a variational Bayesian explanation framework, dubbed ProbAbilistic Concept Explainers (PACE), which models the distributions of patch embeddings to provide trustworthy post-hoc conceptual explanations. Our qualitative analysis reveals the distributions of patch-level concepts, elucidating the effectiveness of ViTs by modeling the joint distribution of patch embeddings and ViT's predictions. Moreover, these patch-level explanations bridge the gap between image-level and dataset-level explanations, thus completing the multi-level structure of PACE. Through extensive experiments on both synthetic and real-world datasets, we demonstrate that PACE surpasses state-of-the-art methods in terms of the defined desiderata.","url_abs":"https://arxiv.org/abs/2406.12649v3","url_pdf":"https://arxiv.org/pdf/2406.12649v3.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":"probabilistic-conceptual-explainers","repo_url":"https://github.com/Wang-ML-Lab/interpretable-foundation-models","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.12649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12649"}},"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/Wang-ML-Lab/interpretable-foundation-models","reach":null}],"summary":{"ran":1,"ran_fixture":1,"ran_violates":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":"53ce46e55205efc8","entry":"Adam","repo":"Wang-ML-Lab/interpretable-foundation-models","repo_kind":"official","path":"PACE/src/model.py","file_url":"https://github.com/Wang-ML-Lab/interpretable-foundation-models/blob/HEAD/PACE/src/model.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":"53ce46e55205efc8"}},{"code_sha256_prefix":"07e18be86a847d82","entry":"contrastive_learning","repo":"Wang-ML-Lab/interpretable-foundation-models","repo_kind":"official","path":"PACE/src/model.py","file_url":"https://github.com/Wang-ML-Lab/interpretable-foundation-models/blob/HEAD/PACE/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"07e18be86a847d82"}},{"code_sha256_prefix":"ef4df3e6f5006749","entry":"dirichlet_expectation","repo":"Wang-ML-Lab/interpretable-foundation-models","repo_kind":"official","path":"PACE/src/model.py","file_url":"https://github.com/Wang-ML-Lab/interpretable-foundation-models/blob/HEAD/PACE/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ef4df3e6f5006749"}},{"code_sha256_prefix":"8d6c2bedc92a8075","entry":"softmax","repo":"Wang-ML-Lab/interpretable-foundation-models","repo_kind":"official","path":"PACE/src/model.py","file_url":"https://github.com/Wang-ML-Lab/interpretable-foundation-models/blob/HEAD/PACE/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d6c2bedc92a8075"}},{"code_sha256_prefix":"8e8b1ac9a1647ab5","entry":"PACE","repo":"Wang-ML-Lab/interpretable-foundation-models","repo_kind":"official","path":"PACE/src/model.py","file_url":"https://github.com/Wang-ML-Lab/interpretable-foundation-models/blob/HEAD/PACE/src/model.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":"8e8b1ac9a1647ab5"}},{"code_sha256_prefix":"f2e1cc81960b0c94","entry":"posterior_mu_sigma","repo":"Wang-ML-Lab/interpretable-foundation-models","repo_kind":"official","path":"PACE/src/model.py","file_url":"https://github.com/Wang-ML-Lab/interpretable-foundation-models/blob/HEAD/PACE/src/model.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":"f2e1cc81960b0c94"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}