UMAD: 自動運転のための教師なしマスクレベル異常検知
UMAD: Unsupervised Mask-Level Anomaly Detection for Autonomous Driving
生成的世界モデルと教師なし画像セグメンテーションを組み合わせ、生のセンサデータのみから異常な交通シーンを検知する手法を提案し、既存の教師なし異常検知を上回る性能を示した。
著者: Daniel Bogdoll, Noël Ollick, Tim Joseph, Svetlana Pavlitska, J. Marius Zöllner
分類: cs.CV, cs.RO
原文アブストラクト
Dealing with atypical traffic scenarios remains a challenging task in autonomous driving. However, most anomaly detection approaches cannot be trained on raw sensor data but require exposure to outlier data and powerful semantic segmentation models trained in a supervised fashion. This limits the representation of normality to labeled data, which does not scale well. In this work, we revisit unsupervised anomaly detection and present UMAD, leveraging generative world models and unsupervised image segmentation. Our method outperforms state-of-the-art unsupervised anomaly detection.
