1 citations · 2 across the 4 of their papers we have counts for
Showing cs.CVShow all
3 papers · 1 filter
cs.CV2024★ 1 cited
Consistent Prompting for Rehearsal-Free Continual Learning
Zhanxin Gao, Jun Cen, Xiaobin Chang
Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on fro…
cs.CV2024
Generalizable Two-Branch Framework for Image Class-Incremental Learning
Chao Wu, Xiaobin Chang, Ruixuan Wang
Deep neural networks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a cat…
cs.CV2023★ 1 cited
Dynamic Residual Classifier for Class Incremental Learning
Xiuwei Chen, Xiaobin Chang
The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With…