{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:44:20Z","timestamp":1773801860723,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"13","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Out-of-distribution (OOD) detection remains a fundamental challenge for deep neural networks, particularly due to overconfident predictions on unseen OOD samples during testing. We reveal a key insight: OOD samples predicted as the same class, or given high probabilities for it, are visually more similar to each other than to the true in-distribution (ID) samples. Motivated by this class-specific observation, we propose DCAC (Dynamic Class-Aware Cache), a training-free, test-time calibration module that maintains separate caches for each ID class to collect high-entropy samples and calibrate the raw predictions of input samples. DCAC leverages cached visual features and predicted probabilities through a lightweight two-layer module to mitigate overconfident predictions on OOD samples. This module can be seamlessly integrated with various existing OOD detection methods across both unimodal and vision-language models while introducing minimal computational overhead. Extensive experiments on multiple OOD benchmarks demonstrate that DCAC significantly enhances existing methods, achieving substantial improvements, i.e., reducing FPR95 by 6.55% when integrated with ASH-S on ImageNet OOD benchmark.<\/jats:p>","DOI":"10.1609\/aaai.v40i13.38057","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:03:05Z","timestamp":1773792185000},"page":"10817-10825","source":"Crossref","is-referenced-by-count":0,"title":["DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectors"],"prefix":"10.1609","volume":"40","author":[{"given":"Yanqi","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qichao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runhe","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhua","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia-Xin","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhilin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weishi","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruixuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38057\/42019","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38057\/42019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:03:05Z","timestamp":1773792185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38057"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i13.38057","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}