为医学图像分割设计像素级风险图，缓解迁移学习中的负面迁移问题。
Transfer Risk Map: Mitigating Pixel-level Negative Transfer in Medical Segmentation
- 基于像素级转移风险图，动态加权微调过程。
- 在FeTS2021上提升4.37%，iSeg2019上提升1.81%。
- 适合处理跨模态、少样本的医学图像分割任务。
如何缓解迁移学习中的负面迁移是长期挑战，尤其在医学图像分割中。现有方法多关注分类或回归任务，忽视了不同图像区域间转移风险的非均匀性。本文提出一种简单有效的加权微调方法，引导模型关注具有高迁移风险的像素区域。具体地，构建一个由可迁移性引导的转移风险图，量化每个像素的迁移难度与负面迁移潜在风险。在微调阶段引入归一化至图像前景大小的地图加权损失函数，以应对类别不平衡问题。大量实验表明，该方法在脑部分割数据集上显著提升目标任务性能：在FeTS2021上提升4.37%，iSeg2019上提升1.81%，有效避免跨模态与跨任务的负面迁移；少样本场景下仍取得2.9%的增益，验证了方法的鲁棒性。
原文摘要 · Abstract (English)
How to mitigate negative transfer in transfer learning is a long-standing and challenging issue, especially in the application of medical image segmentation. Existing methods for reducing negative transfer focus on classification or regression tasks, ignoring the non-uniform negative transfer risk in different image regions. In this work, we propose a simple yet effective weighted fine-tuning method that directs the model's attention towards regions with significant transfer risk for medical semantic segmentation. Specifically, we compute a transferability-guided transfer risk map to quantify the transfer hardness for each pixel and the potential risks of negative transfer. During the fine-tuning phase, we introduce a map-weighted loss function, normalized with image foreground size to counter class imbalance. Extensive experiments on brain segmentation datasets show our method significantly improves the target task performance, with gains of 4.37% on FeTS2021 and 1.81% on iSeg2019, avoiding negative transfer across modalities and tasks. Meanwhile, a 2.9% gain under a few-shot scenario validates the robustness of our approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。