AAAI

BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning

BOFA: 基于CLIP的类增量学习中的桥接层正交低秩融合

Lan Li, Tao Hu, Da-Wei Zhou, Jia-Qi Yang, Han-Jia Ye, De-Chuan Zhan

AI总结 提出BOFA框架，通过将适应限制在CLIP的跨模态桥接层并使用正交低秩融合防止遗忘，无需额外参数或数据回放，实现高效类增量学习。

Comments Accepted by AAAI 2026

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, 40(27): 22967-22975, 2026