物体検出におけるオープンセット誤りを識別するための不確実性推定
Uncertainty for Identifying Open-Set Errors in Visual Object Detection
物体検出器のロジット空間をクラス別ガウス混合モデルでモデル化し、未知クラスへの誤検出を低確率として検出・棄却するリアルタイム手法GMM-Detを提案した。
著者: Dimity Miller, Niko Sünderhauf, Michael Milford, Feras Dayoub
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
Deployed into an open world, object detectors are prone to open-set errors, false positive detections of object classes not present in the training dataset. We propose GMM-Det, a real-time method for extracting epistemic uncertainty from object detectors to identify and reject open-set errors. GMM-Det trains the detector to produce a structured logit space that is modelled with class-specific Gaussian Mixture Models. At test time, open-set errors are identified by their low log-probability under all Gaussian Mixture Models. We test two common detector architectures, Faster R-CNN and RetinaNet, across three varied datasets spanning robotics and computer vision. Our results show that GMM-Det consistently outperforms existing uncertainty techniques for identifying and rejecting open-set detections, especially at the low-error-rate operating point required for safety-critical applications. GMM-Det maintains object detection performance, and introduces only minimal computational overhead. We also introduce a methodology for converting existing object detection datasets into specific open-set datasets to evaluate open-set performance in object detection.
