{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T06:52:06Z","timestamp":1775112726360,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"11","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>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\u2019s high-probability region as the feature\u2019s 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 trade-off. Experiments verify the effectiveness and generalization of LAPS under different architectures and OOD scores.<\/jats:p>","DOI":"10.1609\/aaai.v38i11.29132","type":"journal-article","created":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T10:53:53Z","timestamp":1711364033000},"page":"12402-12410","source":"Crossref","is-referenced-by-count":4,"title":["Exploring Channel-Aware Typical Features for Out-of-Distribution Detection"],"prefix":"10.1609","volume":"38","author":[{"given":"Rundong","family":"He","sequence":"first","affiliation":[]},{"given":"Yue","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Zhongyi","family":"Han","sequence":"additional","affiliation":[]},{"given":"Fan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wan","family":"Su","sequence":"additional","affiliation":[]},{"given":"Yilong","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Tongliang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yongshun","family":"Gong","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2024,3,24]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/29132\/30142","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/29132\/30143","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/29132\/30142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T10:53:54Z","timestamp":1711364034000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/29132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,24]]},"references-count":0,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2024,3,25]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v38i11.29132","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2024,3,24]]}}}