Class-wise Thresholding for Robust Out-of-Distribution Detection
This addresses the issue of sensitivity to label shift in OoD detection methods, which is important for reliable AI deployment, but it is incremental as it builds on existing algorithms.
The paper tackles the problem of out-of-distribution (OoD) detection in deep neural networks by proposing a class-wise thresholding scheme to improve robustness against label shift, achieving similar OoD detection performance even with shifted test distributions.
We consider the problem of detecting OoD(Out-of-Distribution) input data when using deep neural networks, and we propose a simple yet effective way to improve the robustness of several popular OoD detection methods against label shift. Our work is motivated by the observation that most existing OoD detection algorithms consider all training/test data as a whole, regardless of which class entry each input activates (inter-class differences). Through extensive experimentation, we have found that such practice leads to a detector whose performance is sensitive and vulnerable to label shift. To address this issue, we propose a class-wise thresholding scheme that can apply to most existing OoD detection algorithms and can maintain similar OoD detection performance even in the presence of label shift in the test distribution.