Transfer Risk Map: Mitigating Pixel-level Negative Transfer in Medical Segmentation

Overview of transfer risk map guided weighted fine-tuning framework. Red arrows: a transferability-based pixel-level transfer risk map is used to quantify the negative transfer for each pixel; Green arrows: the weighted fine-tuning process, which allows the model’s attention towards regions with significant transfer hardness.

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 focuses 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 transferabilityguided 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 iSeg-2019, avoiding negative transfer across modalities and tasks. Meanwhile, a 2.9% gain under a few-shot scenario validates the robustness of our approach.

Publication

@inproceedings{duan2025transfer,
  title={Transfer Risk Map: Mitigating Pixel-level Negative Transfer in Medical Segmentation},
  author={Duan, Shutong and Yang, Jingyun and Tan, Yang and Zhang, Guoqing and Li, Yang and Zhang, Xiao-Ping},
  booktitle={2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'25)},
  year={2025},
  organization={IEEE},
  note={Accepted}
}

Project list