{"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/mcpnet-an-interpretable-classifier-via-multi","title":"MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes","arxiv_id":"2404.08968","date":"2024-04-13","proceeding":"CVPR 2024 1","authors":["Bor-Shiun Wang","Chien-Yi Wang","Wei-Chen Chiu"],"abstract":"Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept learning during model training. Although being effective in bridging the semantic gap between a model's latent space and human interpretation, these explanation methods only partially reveal the model's decision-making process. The outcome is typically limited to high-level semantics derived from the last feature map. We argue that the explanations lacking insights into the decision processes at low and mid-level features are neither fully faithful nor useful. Addressing this gap, we introduce the Multi-Level Concept Prototypes Classifier (MCPNet), an inherently interpretable model. MCPNet autonomously learns meaningful concept prototypes across multiple feature map levels using Centered Kernel Alignment (CKA) loss and an energy-based weighted PCA mechanism, and it does so without reliance on predefined concept labels. Further, we propose a novel classifier paradigm that learns and aligns multi-level concept prototype distributions for classification purposes via Class-aware Concept Distribution (CCD) loss. Our experiments reveal that our proposed MCPNet while being adaptable to various model architectures, offers comprehensive multi-level explanations while maintaining classification accuracy. Additionally, its concept distribution-based classification approach shows improved generalization capabilities in few-shot classification scenarios.","url_abs":"https://arxiv.org/abs/2404.08968v3","url_pdf":"https://arxiv.org/pdf/2404.08968v3.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":"mcpnet-an-interpretable-classifier-via-multi","repo_url":"https://github.com/NVlabs/MCPNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"xai","task_name":"Explainable Artificial Intelligence (XAI)"}],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.08968","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}