Embedded Prompt Tuning: Towards Enhanced Calibration of Pretrained Models for Medical Images

• URL: http://arxiv.org/abs/2407.01003v2
• Date: Tue, 2 Jul 2024 06:11:43 GMT
• Title: Embedded Prompt Tuning: Towards Enhanced Calibration of Pretrained Models for Medical Images
• Authors: Wenqiang Zu, Shenghao Xie, Qing Zhao, Guoqi Li, Lei Ma,
• Abstract summary: We study the effectiveness of fine-tuning methods when adapting foundation models to medical image classification tasks. We propose the Embedded Prompt Tuning (EPT) method by embedding prompt tokens into the expanded channels. EPT outperforms several state-of-the-art finetuning methods by a significant margin on few-shot medical image classification tasks.
• Score: 18.094731760514264
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation models pre-trained on large-scale data have been widely witnessed to achieve success in various natural imaging downstream tasks. Parameter-efficient fine-tuning (PEFT) methods aim to adapt foundation models to new domains by updating only a small portion of parameters in order to reduce computational overhead. However, the effectiveness of these PEFT methods, especially in cross-domain few-shot scenarios, e.g., medical image analysis, has not been fully explored. In this work, we facilitate the study of the performance of PEFT when adapting foundation models to medical image classification tasks. Furthermore, to alleviate the limitations of prompt introducing ways and approximation capabilities on Transformer architectures of mainstream prompt tuning methods, we propose the Embedded Prompt Tuning (EPT) method by embedding prompt tokens into the expanded channels. We also find that there are anomalies in the feature space distribution of foundation models during pre-training process, and prompt tuning can help mitigate this negative impact. To explain this phenomenon, we also introduce a novel perspective to understand prompt tuning: Prompt tuning is a distribution calibrator. And we support it by analyzing patch-wise scaling and feature separation operations contained in EPT. Our experiments show that EPT outperforms several state-of-the-art fine-tuning methods by a significant margin on few-shot medical image classification tasks, and completes the fine-tuning process within highly competitive time, indicating EPT is an effective PEFT method. The source code is available at github.com/zuwenqiang/EPT.

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)
• Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models [24.62337386603331]
  Large Multi-modal Models (LMMs) are revolutionizing the way machines interact with the world. To adapt LMMs for downstream tasks, parameter-efficient fine-tuning (PEFT) has gained popularity. This paper focuses on the strengths and weaknesses of each tuning strategy, shifting the focus from the efficiency typically associated with these approaches.
  arXiv  Detail & Related papers  (2024-10-29T07:55:50Z)
• 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)
• Probing the Efficacy of Federated Parameter-Efficient Fine-Tuning of Vision Transformers for Medical Image Classification [16.070261684997362]
  Fine-tuning pre-trained models for various downstream tasks is a critical problem in the medical imaging domain. Large size of these models necessitates the use of parameter-efficient fine-tuning (PEFT) to reduce the communication burden in federated learning. In this work, we investigate various federated PEFT strategies for adapting a Vision Transformer (ViT) model for medical image classification.
  arXiv  Detail & Related papers  (2024-07-16T10:28:50Z)
• Test-Time Model Adaptation with Only Forward Passes [68.11784295706995]
  Test-time adaptation has proven effective in adapting a given trained model to unseen test samples with potential distribution shifts. We propose a test-time Forward-Optimization Adaptation (FOA) method. FOA runs on quantized 8-bit ViT, outperforms gradient-based TENT on full-precision 32-bit ViT, and achieves an up to 24-fold memory reduction on ImageNet-C.
  arXiv  Detail & Related papers  (2024-04-02T05:34:33Z)
• Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation [14.71883381837561]
  Cross-domain distribution shift is a significant obstacle to deploying the pre-trained semantic segmentation model in real-world applications. Test-time adaptation has proven its effectiveness in tackling the cross-domain distribution shift during inference. We propose the Visual Prompt-based Test-Time Adaptation (VPTTA) method to train a specific prompt for each test image to align the statistics in the batch normalization layers.
  arXiv  Detail & Related papers  (2023-11-30T09:03:47Z)
• E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning [55.50908600818483]
  Fine-tuning large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. We propose an Effective and Efficient Visual Prompt Tuning (E2VPT) approach for large-scale transformer-based model adaptation. Our approach outperforms several state-of-the-art baselines on two benchmarks.
  arXiv  Detail & Related papers  (2023-07-25T19:03:21Z)
• DVPT: Dynamic Visual Prompt Tuning of Large Pre-trained Models for Medical Image Analysis [30.608225734194416]
  We propose a dynamic visual prompt tuning method, named DVPT, for medical image analysis. It can extract knowledge beneficial to downstream tasks from large models with a few trainable parameters. It can save up to 60% labeled data and 99% storage cost of ViT-B/16.
  arXiv  Detail & Related papers  (2023-07-19T07:11:11Z)
• 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)
• Strong Baselines for Parameter Efficient Few-Shot Fine-tuning [50.83426196335385]
  Few-shot classification (FSC) entails learning novel classes given only a few examples per class after a pre-training (or meta-training) phase. Recent works have shown that simply fine-tuning a pre-trained Vision Transformer (ViT) on new test classes is a strong approach for FSC. Fine-tuning ViTs, however, is expensive in time, compute and storage. This has motivated the design of parameter efficient fine-tuning (PEFT) methods which fine-tune only a fraction of the Transformer's parameters.
  arXiv  Detail & Related papers  (2023-04-04T16:14:39Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.