{"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/odd-one-out-anomaly-detection-by-comparing","title":"Odd-One-Out: Anomaly Detection by Comparing with Neighbors","arxiv_id":"2406.20099","date":"2024-06-28","proceeding":"CVPR 2025 1","authors":["Ankan Bhunia","Changjian Li","Hakan Bilen"],"abstract":"This paper introduces a novel anomaly detection (AD) problem that focuses on identifying `odd-looking' objects relative to the other instances in a given scene. In contrast to the traditional AD benchmarks, anomalies in our task are scene-specific, defined by the regular instances that make up the majority. Since object instances may be only partly visible from a single viewpoint, our setting employs multiple views of each scene as input. To provide a testbed for future research in this task, we introduce two benchmarks, ToysAD-8K and PartsAD-15K. We propose a novel method that constructs 3D object-centric representations from multiple 2D views for each instance and detects the anomalous ones through a cross-instance comparison. We rigorously analyze our method quantitatively and qualitatively on the presented benchmarks.","url_abs":"https://arxiv.org/abs/2406.20099v2","url_pdf":"https://arxiv.org/pdf/2406.20099v2.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":"odd-one-out-anomaly-detection-by-comparing","repo_url":"https://github.com/VICO-UoE/OddOneOutAD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"8k"},{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"odd-one-out","task_name":"Odd One Out"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}