Exploring Channel-Aware Typical Features for Out-of-Distribution Detection
Document Type
Conference Proceeding
Publication Title
Proceedings of the AAAI Conference on Artificial Intelligence
Abstract
Detecting out-of-distribution (OOD) data is essential to ensure the reliability of machine learning models when deployed in real-world scenarios. Different from most previous test-time OOD detection methods that focus on designing OOD scores, we delve into the challenges in OOD detection from the perspective of typicality and regard the feature’s high-probability region as the feature’s typical set. However, the existing typical-feature-based OOD detection method implies an assumption: the proportion of typical feature sets for each channel is fixed. According to our experimental analysis, each channel contributes differently to OOD detection. Adopting a fixed proportion for all channels results in several channels losing too many typical features or incorporating too many abnormal features, resulting in low performance. Therefore, exploring the channel-aware typical features is crucial to better-separating ID and OOD data. Driven by this insight, we propose expLoring channel-Aware tyPical featureS (LAPS). Firstly, LAPS obtains the channel-aware typical set by calibrating the channel-level typical set with the global typical set from the mean and standard deviation. Then, LAPS rectifies the features into channel-aware typical sets to obtain channel-aware typical features. Finally, LAPS leverages the channel-aware typical features to calculate the energy score for OOD detection. Theoretical and visual analyses verify that LAPS achieves a better bias-variance tradeoff. Experiments verify the effectiveness and generalization of LAPS under different architectures and OOD scores.
First Page
12402
Last Page
12410
DOI
10.1609/aaai.v38i11.29132
Publication Date
3-25-2024
Recommended Citation
R. He et al., "Exploring Channel-Aware Typical Features for Out-of-Distribution Detection," Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 11, pp. 12402 - 12410, Mar 2024.
The definitive version is available at https://doi.org/10.1609/aaai.v38i11.29132