{"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-recognition-with-deep-nearest","title":"Visual Recognition with Deep Nearest Centroids","arxiv_id":"2209.07383","date":"2022-09-15","proceeding":null,"authors":["Wenguan Wang","Cheng Han","Tianfei Zhou","Dongfang Liu"],"abstract":"We devise deep nearest centroids (DNC), a conceptually elegant yet surprisingly effective network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most classic and simple classifiers. Current deep models learn the classifier in a fully parametric manner, ignoring the latent data structure and lacking simplicity and explainability. DNC instead conducts nonparametric, case-based reasoning; it utilizes sub-centroids of training samples to describe class distributions and clearly explains the classification as the proximity of test data and the class sub-centroids in the feature space. Due to the distance-based nature, the network output dimensionality is flexible, and all the learnable parameters are only for data embedding. That means all the knowledge learnt for ImageNet classification can be completely transferred for pixel recognition learning, under the \"pre-training and fine-tuning\" paradigm. Apart from its nested simplicity and intuitive decision-making mechanism, DNC can even possess ad-hoc explainability when the sub-centroids are selected as actual training images that humans can view and inspect. Compared with parametric counterparts, DNC performs better on image classification (CIFAR-10, ImageNet) and greatly boots pixel recognition (ADE20K, Cityscapes), with improved transparency and fewer learnable parameters, using various network architectures (ResNet, Swin) and segmentation models (FCN, DeepLabV3, Swin). We feel this work brings fundamental insights into related fields.","url_abs":"https://arxiv.org/abs/2209.07383v2","url_pdf":"https://arxiv.org/pdf/2209.07383v2.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-recognition-with-deep-nearest","repo_url":"https://github.com/chenghan111/dnc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.07383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.07383"}},"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/chenghan111/dnc","reach":null}],"summary":{"ran_fixture":2,"ran_draft_wrong":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":"a92ca6c7bda1b0fe","entry":"approx_ot","repo":"chenghan111/dnc","repo_kind":"official","path":"DNC_classification/mmcls/models/heads/SubCentroids_head_Formal.py","file_url":"https://github.com/chenghan111/dnc/blob/HEAD/DNC_classification/mmcls/models/heads/SubCentroids_head_Formal.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a92ca6c7bda1b0fe"}},{"code_sha256_prefix":"a9f32f28a6eb26c1","entry":"distributed_sinkhorn","repo":"chenghan111/dnc","repo_kind":"official","path":"DNC_classification/mmcls/models/heads/SubCentroids_head_Formal.py","file_url":"https://github.com/chenghan111/dnc/blob/HEAD/DNC_classification/mmcls/models/heads/SubCentroids_head_Formal.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9f32f28a6eb26c1"}},{"code_sha256_prefix":"a9831bac8be98b97","entry":"sinkhorn_knopp","repo":"chenghan111/dnc","repo_kind":"official","path":"DNC_classification/mmcls/models/heads/SubCentroids_head_Formal.py","file_url":"https://github.com/chenghan111/dnc/blob/HEAD/DNC_classification/mmcls/models/heads/SubCentroids_head_Formal.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9831bac8be98b97"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}