Do Multiple Instance Learning Models Transfer?

• URL: http://arxiv.org/abs/2506.09022v2
• Date: Wed, 11 Jun 2025 11:53:38 GMT
• Title: Do Multiple Instance Learning Models Transfer?
• Authors: Daniel Shao, Richard J. Chen, Andrew H. Song, Joel Runevic, Ming Y. Lu, Tong Ding, Faisal Mahmood,
• Abstract summary: Multiple Instance Learning (MIL) is a cornerstone approach in computational pathology (CPath)<n>MIL often struggles with small, weakly supervised clinical datasets.<n>In this study, we evaluate the transfer learning capabilities of pretrained MIL models.
• Score: 7.766368937536295
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Multiple Instance Learning (MIL) is a cornerstone approach in computational pathology (CPath) for generating clinically meaningful slide-level embeddings from gigapixel tissue images. However, MIL often struggles with small, weakly supervised clinical datasets. In contrast to fields such as NLP and conventional computer vision, where transfer learning is widely used to address data scarcity, the transferability of MIL models remains poorly understood. In this study, we systematically evaluate the transfer learning capabilities of pretrained MIL models by assessing 11 models across 21 pretraining tasks for morphological and molecular subtype prediction. Our results show that pretrained MIL models, even when trained on different organs than the target task, consistently outperform models trained from scratch. Moreover, pretraining on pancancer datasets enables strong generalization across organs and tasks, outperforming slide foundation models while using substantially less pretraining data. These findings highlight the robust adaptability of MIL models and demonstrate the benefits of leveraging transfer learning to boost performance in CPath. Lastly, we provide a resource which standardizes the implementation of MIL models and collection of pretrained model weights on popular CPath tasks, available at https://github.com/mahmoodlab/MIL-Lab

Related papers

• Continual Multiple Instance Learning for Hematologic Disease Diagnosis [38.13262557169157]
  We propose the first continual learning method tailored specifically to multiple instance learning (MIL)<n>Our method is rehearsal-based over a selection of single instances from various bags.<n>We show that our method considerably outperforms state-of-the-art methods, providing the first continual learning approach for MIL.
  arXiv  Detail & Related papers  (2025-08-06T12:03:25Z)
• Advancing Multiple Instance Learning with Continual Learning for Whole Slide Imaging [42.60974095443297]
  We analyze CL in the context of attention MIL models and find that the model forgetting is mainly concentrated in the attention layers of the MIL model.<n>We propose two components for improving CL on MIL: Attention Knowledge Distillation (AKD) and the Pseudo-Bag Memory Pool (PMP)
  arXiv  Detail & Related papers  (2025-05-15T18:41:49Z)
• SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images [12.827931905880163]
  This paper proposes to pre-train feature extractor for MIL via a weakly-supervised scheme.<n>To learn effective features for MIL, we delve into several key components, including strong data augmentation, a non-linear prediction head and the robust loss function.<n>We conduct experiments on common large-scale WSI datasets and find it achieves better performance than other pre-training schemes.
  arXiv  Detail & Related papers  (2025-05-10T17:23:36Z)
• Pathological Prior-Guided Multiple Instance Learning For Mitigating Catastrophic Forgetting in Breast Cancer Whole Slide Image Classification [50.899861205016265]
  We propose a new framework PaGMIL to mitigate catastrophic forgetting in breast cancer WSI classification.<n>Our framework introduces two key components into the common MIL model architecture.<n>We evaluate the continual learning performance of PaGMIL across several public breast cancer datasets.
  arXiv  Detail & Related papers  (2025-03-08T04:51:58Z)
• Diffusion-Based Neural Network Weights Generation [80.89706112736353]
  D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning. Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation. Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests [59.623267208433255]
  Multiple Instance Learning (MIL) is a sub-domain of classification problems with positive and negative labels and a "bag" of inputs. In this work, we examine five of the most prominent deep-MIL models and find that none of them respects the standard MIL assumption. We identify and demonstrate this problem via a proposed "algorithmic unit test", where we create synthetic datasets that can be solved by a MIL respecting model.
  arXiv  Detail & Related papers  (2023-10-27T03:05:11Z)
• PDL: Regularizing Multiple Instance Learning with Progressive Dropout Layers [2.069061136213899]
  Multiple instance learning (MIL) was a weakly supervised learning approach that sought to assign binary class labels to collections of instances known as bags. We present a novel approach in the form of a Progressive Dropout Layer (PDL) to address overfitting and empower the MIL model in uncovering intricate and impactful feature representations.
  arXiv  Detail & Related papers  (2023-08-19T21:20:30Z)
• Topologically Regularized Multiple Instance Learning to Harness Data Scarcity [15.06687736543614]
  Multiple Instance Learning models have emerged as a powerful tool to classify patients' microscopy samples. We introduce a topological regularization term to MIL to mitigate this challenge. We show an average enhancement of 2.8% for MIL benchmarks, 15.3% for synthetic MIL datasets, and 5.5% for real-world biomedical datasets over the current state-of-the-art.
  arXiv  Detail & Related papers  (2023-07-26T08:14:18Z)
• Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning [59.38343286807997]
  We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks. Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients. We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-09T17:26:53Z)
• Ensembling Off-the-shelf Models for GAN Training [55.34705213104182]
  We find that pretrained computer vision models can significantly improve performance when used in an ensemble of discriminators. We propose an effective selection mechanism, by probing the linear separability between real and fake samples in pretrained model embeddings. Our method can improve GAN training in both limited data and large-scale settings.
  arXiv  Detail & Related papers  (2021-12-16T18:59:50Z)
• Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources [78.72922528736011]
  We propose a novel approach, black-box adversarial reprogramming (BAR), that repurposes a well-trained black-box machine learning model. Using zeroth order optimization and multi-label mapping techniques, BAR can reprogram a black-box ML model solely based on its input-output responses. BAR outperforms state-of-the-art methods and yields comparable performance to the vanilla adversarial reprogramming method.
  arXiv  Detail & Related papers  (2020-07-17T01:52:34Z)

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.