{"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/deep-nearest-neighbor-anomaly-detection","title":"Deep Nearest Neighbor Anomaly Detection","arxiv_id":"2002.10445","date":"2020-02-24","proceeding":null,"authors":["Liron Bergman","Niv Cohen","Yedid Hoshen"],"abstract":"Nearest neighbors is a successful and long-standing technique for anomaly detection. Significant progress has been recently achieved by self-supervised deep methods (e.g. RotNet). Self-supervised features however typically under-perform Imagenet pre-trained features. In this work, we investigate whether the recent progress can indeed outperform nearest-neighbor methods operating on an Imagenet pretrained feature space. The simple nearest-neighbor based-approach is experimentally shown to outperform self-supervised methods in: accuracy, few shot generalization, training time and noise robustness while making fewer assumptions on image distributions.","url_abs":"https://arxiv.org/abs/2002.10445v1","url_pdf":"https://arxiv.org/pdf/2002.10445v1.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":[],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-on-anomaly-detection-on-2","task":"Anomaly Detection","dataset":"Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102","model":"DN2 CLIP ViT","rank_in_archive_order":3,"of":5,"metrics":{"Network":"ViT","ROC-AUC":"93.2"},"uses_additional_data":true},{"leaderboard":"/sota/anomaly-detection-on-anomaly-detection-on-1","task":"Anomaly Detection","dataset":"Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200","model":"DN2 CLIP ViT","rank_in_archive_order":2,"of":5,"metrics":{"Network":"ViT","ROC-AUC":"93.8"},"uses_additional_data":true},{"leaderboard":"/sota/anomaly-detection-on-one-class-cifar-10","task":"Anomaly Detection","dataset":"One-class CIFAR-10","model":"DN2","rank_in_archive_order":14,"of":36,"metrics":{"AUROC":"92.5"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.10445","atlas_url":"https://app.syntology.ai/?focus=2002.10445","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}