Fine-grained Prompt Tuning: A Parameter and Memory Efficient Transfer Learning Method for High-resolution Medical Image Classification

• URL: http://arxiv.org/abs/2403.07576v4
• Date: Tue, 2 Jul 2024 05:28:03 GMT
• Title: Fine-grained Prompt Tuning: A Parameter and Memory Efficient Transfer Learning Method for High-resolution Medical Image Classification
• Authors: Yijin Huang, Pujin Cheng, Roger Tam, Xiaoying Tang,
• Abstract summary: Fine-grained Prompt Tuning (FPT) is a cost-effective way to transfer pre-trained models to downstream tasks. FPT significantly reduces memory consumption compared to other PETL methods. We evaluate FPT on four medical datasets with varying sizes, modalities, and complexities.
• Score: 1.5791081894226173
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parameter-efficient transfer learning (PETL) is proposed as a cost-effective way to transfer pre-trained models to downstream tasks, avoiding the high cost of updating entire large-scale pre-trained models (LPMs). In this work, we present Fine-grained Prompt Tuning (FPT), a novel PETL method for medical image classification. FPT significantly reduces memory consumption compared to other PETL methods, especially in high-resolution input contexts. To achieve this, we first freeze the weights of the LPM and construct a learnable lightweight side network. The frozen LPM takes high-resolution images as input to extract fine-grained features, while the side network is fed low-resolution images to reduce memory usage. To allow the side network to access pre-trained knowledge, we introduce fine-grained prompts that summarize information from the LPM through a fusion module. Important tokens selection and preloading techniques are employed to further reduce training cost and memory requirements. We evaluate FPT on four medical datasets with varying sizes, modalities, and complexities. Experimental results demonstrate that FPT achieves comparable performance to fine-tuning the entire LPM while using only 1.8% of the learnable parameters and 13% of the memory costs of an encoder ViT-B model with a 512 x 512 input resolution.

Related papers

• FPT+: A Parameter and Memory Efficient Transfer Learning Method for High-resolution Medical Image Classification [1.5791081894226173]
  Fine-grained Prompt Tuning plus (FPT+) is a PETL method designed for high-resolution medical image classification. FPT+ performs transfer learning by training a lightweight side network and accessing pre-trained knowledge from a large pre-trained model. Experimental results demonstrate that FPT+ outperforms other PETL methods, using only 1.03% of the learnable parameters and 3.18% of the memory required for fine-tuning an entire ViT-B model.
  arXiv  Detail & Related papers  (2024-08-05T12:33:07Z)
• 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)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory [69.33445217944029]
  PETL is an effective strategy for adapting pre-trained models to downstream domains. Recent PETL works focus on the more valuable memory-efficient characteristic. We propose a new memory-efficient PETL strategy, Universal Parallel Tuning (UniPT)
  arXiv  Detail & Related papers  (2023-08-28T05:38:43Z)
• 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)
• Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning [6.451743797015637]
  We propose memory-efficient fine-tuning (MEFT) for pre-trained language models. MEFT inserts adapters into a PLM, preserving the PLM's starting point and making it reversible without additional pre-training. MEFT significantly reduces the activation memory up to 84% of full fine-tuning with a negligible amount of trainable parameters.
  arXiv  Detail & Related papers  (2023-06-01T09:26:17Z)
• FastMIM: Expediting Masked Image Modeling Pre-training for Vision [65.47756720190155]
  FastMIM is a framework for pre-training vision backbones with low-resolution input images. It reconstructs Histograms of Oriented Gradients (HOG) feature instead of original RGB values of the input images. It can achieve 83.8%/84.1% top-1 accuracy on ImageNet-1K with ViT-B/Swin-B as backbones.
  arXiv  Detail & Related papers  (2022-12-13T14:09:32Z)
• FPT: Improving Prompt Tuning Efficiency via Progressive Training [84.25195519945215]
  We propose Fast Prompt Tuning to improve prompt tuning's training efficiency. We show that FPT could save over 30% training computations while achieving comparable performance.
  arXiv  Detail & Related papers  (2022-11-13T08:00:29Z)
• Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts [97.20933523766182]
  Prompt tuning is a parameter-efficient tuning (PETuning) method for utilizing pre-trained models (PTMs) We present Late Prompt Tuning () that inserts a late prompt into an intermediate layer of the PTM instead of the input layer or all layers. We show that, can achieve competitive performance to full model tuning and other PETuning methods under both full-data and few-shot scenarios.
  arXiv  Detail & Related papers  (2022-10-20T14:23:52Z)

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.