Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models
Jiahuan Long, Tingsong Jiang, Wen Yao, Yizhe Xiong, Zhengqin Xu, Shuai Jia, Hanqing Liu, Chao Ma
Abstract
Vision foundation models (VFMs) have demonstrated remarkable capabilities in learning universal visual representations. However, adapting these models to downstream tasks conventionally requires parameter updates, with even parameter-efficient fine-tuning methods necessitating the modification of thousands to millions of weights. In this paper, we investigate the redundancies in the segment anything model (SAM) and then propose a novel parameter-free fine-tuning method. Unlike traditional fine-tuning methods that adjust parameters, our method emphasizes selecting, reusing, and enhancing pre-trained features, offering a new perspective on fine-tuning foundation models. Specifically, we introduce a channel selection algorithm based on the model
BibTeX
@inproceedings{aaai2026_parameterfreefin,
title = {Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models},
author = {Jiahuan Long and Tingsong Jiang and Wen Yao and Yizhe Xiong and Zhengqin Xu and Shuai Jia and Hanqing Liu and Chao Ma},
booktitle = {AAAI 2026},
year = {2026}
}