Real-world classifiers can benefit from the option of abstaining from predicting on samples where they have low confidence. Such abstention is particularly useful on samples which are close to the learned decision boundary, or which are outliers with respect to the training sample. These settings have been the subject of extensive but disjoint study in the selective classification (SC) and out-of-distribution (OOD) detection literature. Recent work on selective classification with OOD detection (SCOD) has argued for the unified study of these problems; however, the formal underpinnings of this problem are still nascent, and existing techniques are heuristic in nature. In this paper, we propose new plugin estimators for SCOD that are theoretically grounded, effective, and generalise existing approaches from the SC and OOD detection literature. In the course of our analysis, we formally explicate how naïve use of existing SC and OOD detection baselines may be inadequate for SCOD. We empirically demonstrate that our approaches yields competitive SC and OOD detection performance compared to baselines from both literatures.
School of Computer Science and Technology, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data
1 Embedded Systems Division, Silicon Austria Labs, Graz, Austria;2 Department of Computer Science, University of Innsbruck, Austria;5 Institute of Information Technology, University of Klagenfurt, Austria;3 TU-Graz SAL DES Lab, Silicon Austria Labs, Graz, Austria;4 Institute of Visual Computing, Graz University of Technology, Austria
SeWA: Selective Weight Average via Probabilistic Masking
Huazhong University of Science and Technology(华中科技大学);Shanghai Jiao Tong University(上海交通大学);RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能项目中心);Baidu Inc.(百度公司);Sun Yat-sen University(中山大学);Nanyang Technological University(南洋理工大学)
Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification
Basque Center of Applied Mathematics (BCAM)(巴斯克应用数学中心(BCAM));IKERBASQUE-Basque Foundation for Science(IKERBASQUE-巴斯克科学基金会);University of Michigan(密歇根大学)