PILO: Principal Component-based Implicit Regularization with Low-rank Optimization for Robust Transfer Learning
PILO is established, a new, more effective paradigm for robust transfer learning through principled and targeted parameter optimization, and significantly outperforms state-of-the-art full-parameter and parameter-efficient methods in robust accuracy across multiple benchmarks.
Shuaihe Liu, Qiugang Zhan, Guisong Liu et al.
· 0 citations