Preprint
Jul 2026
DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning
The Decoupled Representation Dynamic Network is proposed, which addresses two intertwined challenges: cross-task confusion from sequential training on predominantly current-task data, which biases decision boundaries toward recent tasks; and under-optimized shared representations in the backbone that cap long-term discriminability as tasks accumulate.
Bin Huang, Yifu Chen, Zhilin Wang et al.
· 0 citations