English

SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images

Computer Vision and Pattern Recognition 2025-05-13 v1

Abstract

Various multi-instance learning (MIL) based approaches have been developed and successfully applied to whole-slide pathological images (WSI). Existing MIL methods emphasize the importance of feature aggregators, but largely neglect the instance-level representation learning. They assume that the availability of a pre-trained feature extractor can be directly utilized or fine-tuned, which is not always the case. This paper proposes to pre-train feature extractor for MIL via a weakly-supervised scheme, i.e., propagating the weak bag-level labels to the corresponding instances for supervised learning. To learn effective features for MIL, we further delve into several key components, including strong data augmentation, a non-linear prediction head and the robust loss function. We conduct experiments on common large-scale WSI datasets and find it achieves better performance than other pre-training schemes (e.g., ImageNet pre-training and self-supervised learning) in different downstream tasks. We further show the compatibility and scalability of the proposed scheme by deploying it in fine-tuning the pathological-specific models and pre-training on merged multiple datasets. To our knowledge, this is the first work focusing on the representation learning for MIL.

Keywords

Cite

@article{arxiv.2505.06710,
  title  = {SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images},
  author = {Yicheng Song and Tiancheng Lin and Die Peng and Su Yang and Yi Xu},
  journal= {arXiv preprint arXiv:2505.06710},
  year   = {2025}
}
R2 v1 2026-06-28T23:28:15.193Z