{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:03:27Z","timestamp":1773803007121,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"25","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Non-Exemplar Class Incremental Learning (NECIL) strives to preserve classification performance in an evolving data stream without revisiting old-class exemplars. Current methods mitigate catastrophic forgetting by replaying and augmenting historical prototypes as surrogates for old classes. However, they treat prototypes as holistic representations for global-level augmentations, which overlook dimensional semantic disparity and old-new class relationships, failing to maintain old-class discriminability and adaptability to the evolving feature space. To address this challenge, we propose Dimensionally-Allocated Prototype Refinement (DiAPR), a granular framework that progressively refines prototypes to exhibit class separability in the new feature space through three modules. Specifically, Distribution-aware Pairing (DAP) captures old-new class semantic consistency to guide Granular Semantic Allocation (GSA) in dimension-wise conflation, while Cross-Dimensional Transition (CDT) enhances cross-dimensional dependencies. The resulting prototypes sharpen classifier decision boundaries. Moreover, CDT inherently enables softened feature alignment, thereby yielding a more compatible feature space. Extensive experiments demonstrate DiAPR\u2019s superiority, with improvements over SOTA by 2.35%, 0.70%, 0.96% on three CIFAR-100 settings, 1.03%, 0.54%, 0.40% on Tiny-ImageNet, and 0.60% on ImageNet-Subset.<\/jats:p>","DOI":"10.1609\/aaai.v40i25.39263","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:18:25Z","timestamp":1773796705000},"page":"21189-21197","source":"Crossref","is-referenced-by-count":0,"title":["DiAPR: Dimensionally-Allocated Prototype Refinement for Non-Exemplar Class Incremental Learning"],"prefix":"10.1609","volume":"40","author":[{"given":"Ruixuan","family":"Gao","sequence":"first","affiliation":[]},{"given":"Qijun","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Keren","family":"Fu","sequence":"additional","affiliation":[]}],"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\/39263\/43224","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39263\/43224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:18:26Z","timestamp":1773796706000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/39263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"25","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i25.39263","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]]}}}