arXiv 2603.004332026-02-28cs.CVcs.AI

TAP-SLF：面向多任务超声图像分析的视觉基础模型参数高效适应

TAP-SLF: Parameter-Efficient Adaptation of Vision Foundation Models for Multi-Task Ultrasound Image Analysis

College of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China（计算机科学与工程学院，重庆科技学院，重庆）

Hui Wan, Libin Lan

备注：: 4 pages, 2 figures, 4 tables; Submitted to ISBI FMC UIA 2026; Our code is publicly available at https://github.com/huiwanHW/Florence-2-adaptation

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

TAP-SLF通过任务感知提示和选择性层微调，实现视觉基础模型在多任务超声图像分析中的高效适应。

摘要：

在医学图像分析中同时执行分割、分类、检测和回归等任务时，往往面临模型通用性和共享特征表示优化的重大挑战。尽管视觉基础模型（VFMs）提供了强大的通用表示，但对有限的医学数据进行全微调容易过拟合且计算成本高。此外，现有的参数高效微调方法通常采用任务无关的适应协议，忽视了任务特定机制和模型层在微调中的敏感性差异。在本工作中，我们提出了任务感知提示和选择性层微调（TAP-SLF），一种用于多任务超声图像分析的统一框架。TAP-SLF结合任务感知的软提示将任务特定先验编码到输入令牌序列中，并应用LoRA对选定的特定顶层编码器进行微调。该策略仅更新VFM参数的小部分，同时保持预训练骨干网络冻结。通过结合任务感知提示与选择性高层微调，TAP-SLF能够在共享骨干网络内高效地将VFM适应于多种医学任务。在FMC_UIA 2026挑战测试集上的结果，其中TAP-SLF获得第五名，结合使用8:2训练测试分割的官方发布训练数据集评估，表明任务感知提示和选择性层微调是高效VFM适应的有效策略。

英文摘要：

Executing multiple tasks simultaneously in medical image analysis, including segmentation, classification, detection, and regression, often introduces significant challenges regarding model generalizability and the optimization of shared feature representations. While Vision Foundation Models (VFMs) provide powerful general representations, full fine-tuning on limited medical data is prone to overfitting and incurs high computational costs. Moreover, existing parameter-efficient fine-tuning approaches typically adopt task-agnostic adaptation protocols, overlooking both task-specific mechanisms and the varying sensitivity of model layers during fine-tuning. In this work, we propose Task-Aware Prompting and Selective Layer Fine-Tuning (TAP-SLF), a unified framework for multi-task ultrasound image analysis. TAP-SLF incorporates task-aware soft prompts to encode task-specific priors into the input token sequence and applies LoRA to selected specific top layers of the encoder. This strategy updates only a small fraction of the VFM parameters while keeping the pre-trained backbone frozen. By combining task-aware prompts with selective high-layer fine-tuning, TAP-SLF enables efficient VFM adaptation to diverse medical tasks within a shared backbone. Results on the FMC_UIA 2026 Challenge test set, where TAP-SLF wins fifth place, combined with evaluations on the officially released training dataset using an 8:2 train-test split, demonstrate that task-aware prompting and selective layer tuning are effective strategies for efficient VFM adaptation.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。