论文标题
评估开放式识别的不确定性校准
Evaluating Uncertainty Calibration for Open-Set Recognition
论文作者
论文摘要
尽管在视觉分类问题的预测准确性方面取得了巨大的成功，但深层神经网络（DNN）仍无法在分布式（OOD）数据上提供过度支持概率。然而，准确的不确定性估计对于安全可靠的机器人自主权至关重要。在本文中，我们以与OOD数据上的常规评估校准方法明显不同的方式评估了开放式条件的流行校准技术。我们的结果表明，封闭设置的DNN校准方法对于开放式识别的有效性要差得多，这突出了开发新的DNN校准方法来解决此问题的必要性。
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.
