2 papers
cs.AI2026
Socialized Division and Collaboration: Rethinking Class-Incremental Learning under Optimization Conflicts
Xinjie Yao, Zhihe Fan, Yunqi Zhu +6
Class-incremental learning is commonly instantiated as a single-model paradigm, where a unified model sequentially adapts to an unbounded stream of sessions. While effective under…
cs.LG2025
Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds
Huitong Chen, Yu Wang, Yan Fan +2
Class incremental learning (CIL) aims to enable models to continuously learn new classes without catastrophically forgetting old ones. A promising direction is to learn and use pro…