Odd-One-Out: Anomaly Detection by Comparing with Neighbors

Autor:	Bhunia, Ankan, Li, Changjian, Bilen, Hakan
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	This paper introduces a novel anomaly detection (AD) problem that focuses on identifying `odd-looking' objects relative to the other instances within a scene. Unlike the traditional AD benchmarks, in our setting, anomalies in this context are scene-specific, defined by the regular instances that make up the majority. Since object instances are often partly visible from a single viewpoint, our setting provides 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 generates 3D object-centric representations for each instance and detects the anomalous ones through a cross-examination between the instances. We rigorously analyze our method quantitatively and qualitatively in the presented benchmarks. Comment: Codes & Dataset at https://github.com/VICO-UoE/OddOneOutAD
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2406.20099 Zobrazit plný text záznamu View this record from Arxiv