オープンセット認識における不確実性キャリブレーションの評価
Evaluating Uncertainty Calibration for Open-Set Recognition
ロボットの安全な自律性に重要な不確実性推定について、既存のキャリブレーション手法がオープンセット認識では効果が低いことを示した評価研究。
著者: Zongyao Lyu, Nolan B. Gutierrez, William J. Beksi
分類: cs.CV, cs.RO
原文アブストラクト
Despite achieving enormous success in predictive accuracy for visual classification problems, deep neural networks (DNNs) suffer from providing overconfident probabilities on out-of-distribution (OOD) data. Yet, accurate uncertainty estimation is crucial for safe and reliable robot autonomy. In this paper, we evaluate popular calibration techniques for open-set conditions in a way that is distinctly different from the conventional evaluation of calibration methods on OOD data. Our results show that closed-set DNN calibration approaches are much less effective for open-set recognition, which highlights the need to develop new DNN calibration methods to address this problem.
