Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation
- URL: http://arxiv.org/abs/2510.07823v1
- Date: Thu, 09 Oct 2025 06:08:15 GMT
- Title: Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation
- Authors: Shohei Enomoto,
- Abstract summary: Visual prompting (VP) has emerged as a promising parameter-efficient fine-tuning approach for adapting pre-trained vision models to downstream tasks.<n>We propose ACAVP (Affine, Color, and Additive Visual Prompting), which enhances VP's expressive power by introducing complementary transformation operations.<n>We show that ACAVP achieves state-of-the-art accuracy among VP methods, surpasses linear probing in average accuracy, and exhibits superior robustness to distribution shifts.
- Score: 0.9137554315375919
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Visual prompting (VP) has emerged as a promising parameter-efficient fine-tuning approach for adapting pre-trained vision models to downstream tasks without modifying model parameters. Despite offering advantages like negligible computational overhead and compatibility with black-box models, conventional VP methods typically achieve lower accuracy than other adaptation approaches. Our analysis reveals two critical limitations: the restricted expressivity of simple additive transformation and a tendency toward overfitting when the parameter count increases. To address these challenges, we propose ACAVP (Affine, Color, and Additive Visual Prompting), which enhances VP's expressive power by introducing complementary transformation operations: affine transformation for creating task-specific prompt regions while preserving original image information, and color transformation for emphasizing task-relevant visual features. Additionally, we identify that overfitting is a critical issue in VP training and introduce TrivialAugment as an effective data augmentation, which not only benefits our approach but also significantly improves existing VP methods, with performance gains of up to 12 percentage points on certain datasets. This demonstrates that appropriate data augmentation is universally beneficial for VP training. Extensive experiments across twelve diverse image classification datasets with two different model architectures demonstrate that ACAVP achieves state-of-the-art accuracy among VP methods, surpasses linear probing in average accuracy, and exhibits superior robustness to distribution shifts, all while maintaining minimal computational overhead during inference.
Related papers
- Visual Fourier Prompt Tuning [63.66866445034855]
We propose the Visual Fourier Prompt Tuning (VFPT) method as a general and effective solution for adapting large-scale transformer-based models.
Our approach incorporates the Fast Fourier Transform into prompt embeddings and harmoniously considers both spatial and frequency domain information.
Our results demonstrate that our approach outperforms current state-of-the-art baselines on two benchmarks.
arXiv Detail & Related papers (2024-11-02T18:18:35Z) - CVPT: Cross Visual Prompt Tuning [15.642102189777072]
Cross Visual Prompt Tuning (CVPT) is a cross-attention module to model interactions between prompts and image tokens.<n>CVPT achieves over 4% higher average accuracy, rivaling leading adapter-based methods in both performance and efficiency.<n>Our work confirms that prompt-based methods can achieve exceptional results in visual fine-tuning.
arXiv Detail & Related papers (2024-08-27T11:07:19Z) - Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization.
A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR.
For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
arXiv Detail & Related papers (2024-07-11T10:35:53Z) - Enhancing Generalization in Medical Visual Question Answering Tasks via
Gradient-Guided Model Perturbation [16.22199565010318]
We introduce a method that incorporates gradient-guided perturbations to the visual encoder of the multimodality model during both pre-training and fine-tuning phases.
The results show that, even with a significantly smaller pre-training image caption dataset, our approach achieves competitive outcomes.
arXiv Detail & Related papers (2024-03-05T06:57:37Z) - HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain
Generalization [69.33162366130887]
Domain Generalization (DG) endeavors to create machine learning models that excel in unseen scenarios by learning invariant features.
We introduce a novel method designed to supplement the model with domain-level and task-specific characteristics.
This approach aims to guide the model in more effectively separating invariant features from specific characteristics, thereby boosting the generalization.
arXiv Detail & Related papers (2024-01-18T04:23:21Z) - VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness [56.87603097348203]
VeCAF uses labels and natural language annotations to perform parametric data selection for PVM finetuning.
VeCAF incorporates the finetuning objective to select significant data points that effectively guide the PVM towards faster convergence.
On ImageNet, VeCAF uses up to 3.3x less training batches to reach the target performance compared to full finetuning.
arXiv Detail & Related papers (2024-01-15T17:28:37Z) - p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models [10.713680139939354]
Vision-Language models (VLMs) pre-trained on large corpora have demonstrated notable success across a range of downstream tasks.
PETL has garnered attention as a viable alternative to full fine-tuning.
We propose a new adapter architecture, $p$-adapter, which employs $p$-Laplacian message passing in Graph Neural Networks (GNNs)
arXiv Detail & Related papers (2023-12-17T05:30:35Z) - Hierarchical Side-Tuning for Vision Transformers [33.536948382414316]
Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks.
PETL has shown potential for achieving high performance with fewer parameter updates compared to full fine-tuning.
This paper introduces Hierarchical Side-Tuning (HST), an innovative PETL method facilitating the transfer of ViT models to diverse downstream tasks.
arXiv Detail & Related papers (2023-10-09T04:16:35Z) - Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer [54.32283739486781]
We present a textbfForgery-aware textbfAdaptive textbfVision textbfTransformer (FA-ViT) under the adaptive learning paradigm.
FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation.
arXiv Detail & Related papers (2023-09-20T06:51:11Z) - 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) - Adversarial Feature Augmentation and Normalization for Visual
Recognition [109.6834687220478]
Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models.
Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings.
We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
arXiv Detail & Related papers (2021-03-22T20:36:34Z)
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.