{"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/advisingnets-learning-to-distinguish-correct","title":"PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans","arxiv_id":"2308.13651","date":"2023-08-25","proceeding":null,"authors":["Giang","Nguyen","Valerie Chen","Mohammad Reza Taesiri","Anh Totti Nguyen"],"abstract":"Nearest neighbors (NN) are traditionally used to compute final decisions, e.g., in Support Vector Machines or k-NN classifiers, and to provide users with explanations for the model's decision. In this paper, we show a novel utility of nearest neighbors: To improve predictions of a frozen, pretrained image classifier C. We leverage an image comparator S that (1) compares the input image with NN images from the top-K most probable classes given by C; and (2) uses scores from S to weight the confidence scores of C to refine predictions. Our method consistently improves fine-grained image classification accuracy on CUB-200, Cars-196, and Dogs-120. Also, a human study finds that showing users our probable-class nearest neighbors (PCNN) reduces over-reliance on AI, thus improving their decision accuracy over prior work which only shows only the most-probable (top-1) class examples.","url_abs":"https://arxiv.org/abs/2308.13651v5","url_pdf":"https://arxiv.org/pdf/2308.13651v5.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":"advisingnets-learning-to-distinguish-correct","repo_url":"https://github.com/anguyen8/nearest-neighbor-XAI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"advisingnets-learning-to-distinguish-correct","repo_url":"https://github.com/giangnguyen2412/PCNN-src-code-TMRL2024","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"xai","task_name":"Explainable Artificial Intelligence (XAI)"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"pcnn-ranking","method_name":"PCNN Ranking"},{"method_slug":"k-nn","method_name":"k-NN"}],"datasets_introduced":[],"methods_introduced":[{"slug":"pcnn-ranking","name":"PCNN Ranking","full_name":"Probable-Class Nearest-Neighbor Ranking"}],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-cub-200","task":"Fine-Grained Image Classification","dataset":"CUB-200-2011","model":"ResNet-50","rank_in_archive_order":6,"of":12,"metrics":{"Accuracy":"88.59%"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-cub-200-1","task":"Fine-Grained Image Classification","dataset":"CUB-200-2011","model":"ResNet-50","rank_in_archive_order":20,"of":30,"metrics":{"Accuracy":"88.59"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","task":"Fine-Grained Image Classification","dataset":"Stanford Cars","model":"ResNet-50","rank_in_archive_order":76,"of":83,"metrics":{"Accuracy":"91.06%"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford-1","task":"Fine-Grained Image Classification","dataset":"Stanford Dogs","model":"ResNet-50","rank_in_archive_order":22,"of":24,"metrics":{"Accuracy":"86.31%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}