Revisiting the Power of Prompt for Visual Tuning

• URL: http://arxiv.org/abs/2402.02382v3
• Date: Mon, 27 May 2024 06:51:07 GMT
• Title: Revisiting the Power of Prompt for Visual Tuning
• Authors: Yuzhu Wang, Lechao Cheng, Chaowei Fang, Dingwen Zhang, Manni Duan, Meng Wang,
• Abstract summary: This study explores the correlation evolvement between prompts and patch tokens during proficient training. Inspired by the observation that the prompt tokens tend to share high mutual information with patch tokens, we propose initializing prompts with downstream token prototypes. Our method significantly advances the adaptation for self-supervised pretraining, achieving impressive task performance gains of at least 10% to 30%.
• Score: 50.11465784194896
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual prompt tuning (VPT) is a promising solution incorporating learnable prompt tokens to customize pre-trained models for downstream tasks. However, VPT and its variants often encounter challenges like prompt initialization, prompt length, and subpar performance in self-supervised pretraining, hindering successful contextual adaptation. This study commences by exploring the correlation evolvement between prompts and patch tokens during proficient training. Inspired by the observation that the prompt tokens tend to share high mutual information with patch tokens, we propose initializing prompts with downstream token prototypes. The strategic initialization, a stand-in for the previous initialization, substantially improves performance in fine-tuning. To refine further, we optimize token construction with a streamlined pipeline that maintains excellent performance with almost no increase in computational expenses compared to VPT. Exhaustive experiments show our proposed approach outperforms existing methods by a remarkable margin. For instance, it surpasses full fine-tuning in 19 out of 24 tasks, using less than 0.4% of learnable parameters on the FGVC and VTAB-1K benchmarks. Notably, our method significantly advances the adaptation for self-supervised pretraining, achieving impressive task performance gains of at least 10% to 30%. Besides, the experimental results demonstrate the proposed SPT is robust to prompt lengths and scales well with model capacity and training data size. We finally provide an insightful exploration into the amount of target data facilitating the adaptation of pre-trained models to downstream tasks. The code is available at https://github.com/WangYZ1608/Self-Prompt-Tuning.

Related papers

• CVPT: Cross-Attention help Visual Prompt Tuning adapt visual task [15.642102189777072]
  Cross Visual Prompt Tuning is a new type of visual fine-tuning. CVPT calculates cross-attention between the prompt tokens and the embedded tokens, which allows us to compute the semantic relationship between them. CVPT significantly improves VPT's performance and efficiency in visual tasks.
  arXiv  Detail & Related papers  (2024-08-27T11:07:19Z)
• Approximated Prompt Tuning for Vision-Language Pre-trained Models [54.326232586461614]
  In vision-language pre-trained models, prompt tuning often requires a large number of learnable tokens to bridge the gap between the pre-training and downstream tasks. We propose a novel Approximated Prompt Tuning (APT) approach towards efficient VL transfer learning.
  arXiv  Detail & Related papers  (2023-06-27T05:43:47Z)
• Do We Really Need a Large Number of Visual Prompts? [23.85637456240694]
  We analyze the impact of the number of prompts on fine-tuning performance and self-attention operation in a vision transformer architecture. We propose a Prompt Condensation (PC) technique that aims to prevent performance degradation from using a small number of prompts.
  arXiv  Detail & Related papers  (2023-05-26T19:31:57Z)
• Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models [108.13378788663196]
  We propose Subspace Prompt Tuning (SubPT) to project the gradients in back-propagation onto the low-rank subspace spanned by the early-stage gradient flow eigenvectors during the entire training process. We equip CoOp with Novel Learner Feature (NFL) to enhance the generalization ability of the learned prompts onto novel categories beyond the training set.
  arXiv  Detail & Related papers  (2022-11-04T02:06:22Z)
• Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models [107.05966685291067]
  We propose test-time prompt tuning (TPT) to learn adaptive prompts on the fly with a single test sample. TPT improves the zero-shot top-1 accuracy of CLIP by 3.6% on average. In evaluating cross-dataset generalization with unseen categories, TPT performs on par with the state-of-the-art approaches that use additional training data.
  arXiv  Detail & Related papers  (2022-09-15T17:55:11Z)
• Instance-wise Prompt Tuning for Pretrained Language Models [72.74916121511662]
  Instance-wise Prompt Tuning (IPT) is the first prompt learning paradigm that injects knowledge from the input data instances to the prompts. IPT significantly outperforms task-based prompt learning methods, and achieves comparable performance to conventional finetuning with only 0.5% - 1.5% of tuned parameters.
  arXiv  Detail & Related papers  (2022-06-04T10:08:50Z)
• Learning a Better Initialization for Soft Prompts via Meta-Learning [58.53984967461313]
  We propose MetaPT (Meta-learned Prompt Tuning) to improve prompt tuning. We introduce the structure by first clustering pre-training data into different auxiliary tasks. We use these tasks to pre-train prompts with a meta-learning algorithm.
  arXiv  Detail & Related papers  (2022-05-25T03:50:23Z)
• PPT: Pre-trained Prompt Tuning for Few-shot Learning [47.05554619258627]
  Prompts for pre-trained language models (PLMs) have shown remarkable performance by bridging the gap between pre-training tasks and various downstream tasks. Among these methods, prompt tuning, which freezes PLMs and only tunes soft prompts, provides an efficient and effective solution for adapting large-scale PLMs to downstream tasks. In our work, we find that prompt tuning performs comparably with conventional full-model fine-tuning when downstream data are sufficient, whereas it performs much worse under few-shot learning settings.
  arXiv  Detail & Related papers  (2021-09-09T15:11:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.