Beyond efficient fine-tuning: Efficient hybrid fine-tuning of CLIP models guided by explainable ViT attention.

@article{ye-2026-beyond, author = {Hui Ye and Xuri Ge and Junqi Wang and Junchen Fu and Xin Xin and Jiao Xue and Yao Chen and Pengjie Ren and Zhumin Chen}, title = {{Beyond efficient fine-tuning: Efficient hybrid fine-tuning of CLIP models guided by explainable ViT attention}}, journal = {Information Processing and Management}, volume = {63}, number = {5}, pages = {104628}, year = {2026}, url = {https://doi.org/10.1016/J.IPM.2026.104628}, doi = {https://doi.org/10.1016/J.IPM.2026.104628} }