3 papers
cs.CV2026
Continual-MEGA: A Large-scale Benchmark for Generalizable Continual Anomaly Detection
Geonu Lee, Yujeong Oh, Geonhui Jang +4
In this paper, we introduce a new benchmark for continual learning in anomaly detection, aimed at better reflecting real-world deployment scenarios. Our benchmark, Continual-MEGA,…
cs.CV2025
CoT-Segmenter: Enhancing OOD Detection in Dense Road Scenes via Chain-of-Thought Reasoning
Jeonghyo Song, Kimin Yun, DaeUng Jo +2
Effective Out-of-Distribution (OOD) detection is criti-cal for ensuring the reliability of semantic segmentation models, particularly in complex road environments where safety and…
cs.CV2025
Distributional Uncertainty for Out-of-Distribution Detection
JinYoung Kim, DaeUng Jo, Kimin Yun +2
Estimating uncertainty from deep neural networks is a widely used approach for detecting out-of-distribution (OoD) samples, which typically exhibit high predictive uncertainty. How…