{"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/interpretable-image-classification-with-1","title":"Interpretable Image Classification with Adaptive Prototype-based Vision Transformers","arxiv_id":"2410.20722","date":"2024-10-28","proceeding":null,"authors":["Chiyu Ma","Jon Donnelly","Wenjun Liu","Soroush Vosoughi","Cynthia Rudin","Chaofan Chen"],"abstract":"We present ProtoViT, a method for interpretable image classification combining deep learning and case-based reasoning. This method classifies an image by comparing it to a set of learned prototypes, providing explanations of the form ``this looks like that.'' In our model, a prototype consists of \\textit{parts}, which can deform over irregular geometries to create a better comparison between images. Unlike existing models that rely on Convolutional Neural Network (CNN) backbones and spatially rigid prototypes, our model integrates Vision Transformer (ViT) backbones into prototype based models, while offering spatially deformed prototypes that not only accommodate geometric variations of objects but also provide coherent and clear prototypical feature representations with an adaptive number of prototypical parts. Our experiments show that our model can generally achieve higher performance than the existing prototype based models. Our comprehensive analyses ensure that the prototypes are consistent and the interpretations are faithful.","url_abs":"https://arxiv.org/abs/2410.20722v1","url_pdf":"https://arxiv.org/pdf/2410.20722v1.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":"interpretable-image-classification-with-1","repo_url":"https://github.com/Henrymachiyu/ProtoViT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.20722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20722"}},"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/Henrymachiyu/ProtoViT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"da0f80d54b852951","entry":"create_logger","repo":"Henrymachiyu/ProtoViT","repo_kind":"official","path":"log.py","file_url":"https://github.com/Henrymachiyu/ProtoViT/blob/HEAD/log.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da0f80d54b852951"}},{"code_sha256_prefix":"a578552e64b8de7e","entry":"find_high_activation_crop","repo":"Henrymachiyu/ProtoViT","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/Henrymachiyu/ProtoViT/blob/HEAD/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a578552e64b8de7e"}},{"code_sha256_prefix":"c9e92d0b7ff929fe","entry":"list_of_distances","repo":"Henrymachiyu/ProtoViT","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/Henrymachiyu/ProtoViT/blob/HEAD/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9e92d0b7ff929fe"}},{"code_sha256_prefix":"2f5c8689a7884f62","entry":"preprocess","repo":"Henrymachiyu/ProtoViT","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/Henrymachiyu/ProtoViT/blob/HEAD/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f5c8689a7884f62"}},{"code_sha256_prefix":"d22fdfbc49113693","entry":"preprocess_input_function","repo":"Henrymachiyu/ProtoViT","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/Henrymachiyu/ProtoViT/blob/HEAD/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d22fdfbc49113693"}},{"code_sha256_prefix":"efb86a8611f14f72","entry":"undo_preprocess","repo":"Henrymachiyu/ProtoViT","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/Henrymachiyu/ProtoViT/blob/HEAD/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"efb86a8611f14f72"}},{"code_sha256_prefix":"1b73c64fe6759663","entry":"update_prototypes_on_batch","repo":"Henrymachiyu/ProtoViT","repo_kind":"official","path":"push_greedy.py","file_url":"https://github.com/Henrymachiyu/ProtoViT/blob/HEAD/push_greedy.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b73c64fe6759663"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}