Visual Tuning
arXiv:2305.06061 · doi:10.1145/3657632
Abstract
Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that fine-tunes the whole pre-trained model or just the fully connected layer. Instead, recent advances can achieve superior performance than full-tuning the whole pre-trained parameters by updating far fewer parameters, enabling edge devices and downstream applications to reuse the increasingly large foundation models deployed on the cloud. With the aim of helping researchers get the full picture and future directions of visual tuning, this survey characterizes a large and thoughtful selection of recent works, providing a systematic and comprehensive overview of existing work and models. Specifically, it provides a detailed background of visual tuning and categorizes recent visual tuning techniques into five groups: prompt tuning, adapter tuning, parameter tuning, and remapping tuning. Meanwhile, it offers some exciting research directions for prospective pre-training and various interactions in visual tuning.
37 pages. Accepted to ACM CSUR
References in corpus (4)
- NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
- Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks
- Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
- Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models