Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detection
This addresses a critical safety issue for deploying neural networks in real-world applications, but it is an incremental improvement over existing methods.
The paper tackles the problem of neural networks making overconfident predictions on out-of-distribution (OOD) data by proposing a post-hoc OOD detection method using feature masking and logit smoothing, achieving new state-of-the-art performance on multiple benchmarks.
Out-of-distribution (OOD) detection is essential when deploying neural networks in the real world. One main challenge is that neural networks often make overconfident predictions on OOD data. In this study, we propose an effective post-hoc OOD detection method based on a new feature masking strategy and a novel logit smoothing strategy. Feature masking determines the important features at the penultimate layer for each in-distribution (ID) class based on the weights of the ID class in the classifier head and masks the rest features. Logit smoothing computes the cosine similarity between the feature vector of the test sample and the prototype of the predicted ID class at the penultimate layer and uses the similarity as an adaptive temperature factor on the logit to alleviate the network's overconfidence prediction for OOD data. With these strategies, we can reduce feature activation of OOD data and enlarge the gap in OOD score between ID and OOD data. Extensive experiments on multiple standard OOD detection benchmarks demonstrate the effectiveness of our method and its compatibility with existing methods, with new state-of-the-art performance achieved from our method. The source code will be released publicly.