2023/10/10 by Wei Dong, Dong, Wei, Dawei Yan +5 · 2 citations
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Image Enhancement Techniques #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2310.06234
openalex publication_date 2023/10/10 · openalex created_date 2023/10/12 · openalex updated_date 2026/07/28
The advent of high-capacity pre-trained models has revolutionized problem-solving in computer vision, shifting the focus from training task-specific models to adapting pre-trained models. Consequently, effectively adapting large pre-trained models to downstream tasks in an efficient manner has become a prominent research area. Existing solutions primarily concentrate on designing lightweight adapters and their interaction with pre-trained models, with the goal of minimizing the number of parameters requiring updates. In this study, we propose a novel Adapter Re-Composing (ARC) strategy that addresses efficient pre-trained model adaptation from a fresh perspective. Our approach considers the reusability of adaptation parameters and introduces a parameter-sharing scheme. Specifically, we leverage symmetric down-/up-projections to construct bottleneck operations, which are shared across layers. By learning low-dimensional re-scaling coefficients, we can effectively re-compose layer-adaptive adapters. This parameter-sharing strategy in adapter design allows us to significantly reduce the number of new parameters while maintaining satisfactory performance, thereby offering a promising approach to compress the adaptation cost. We conduct experiments on 24 downstream image classification tasks using various Vision Transformer variants to evaluate our method. The results demonstrate that our approach achieves compelling transfer learning performance with a reduced parameter count. Our code is available at \hrefhttps://github.com/DavidYanAnDe/ARChttps://github.com/DavidYanAnDe/ARC.