WeakSupCon: Weakly Supervised Contrastive Learning for Encoder Pre-training

2025-03-06

AI Summary

In weakly supervised multiple-instance learning (MIL), only bag-level labels are available, making it challenging to identify discriminative instance-level features. Method: We propose a novel bag-level label-driven encoder pretraining paradigm. Its core innovation is the first integration of bag-level supervision into contrastive learning via a multi-task weakly supervised contrastive loss, which encourages intra-bag instance feature aggregation and inter-bag inter-class separation—thereby mitigating domain shift and class confusion. The method jointly optimizes weakly supervised contrastive learning, multi-task objectives, and instance embedding alignment. Results: Evaluated on three pathological whole-slide image (WSI) datasets, our approach significantly outperforms ImageNet pretraining, self-supervised pretraining, and end-to-end MIL methods, empirically validating the effectiveness of bag-level labels as supervisory signals for representation learning.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Representation Learning for Vision
• Multiagent Systems: Multiagent Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Weakly supervised multiple instance learning (MIL) is a challenging task given that only bag-level labels are provided, while each bag typically contains multiple instances. This topic has been extensively studied in histopathological image analysis, where labels are usually available only at the whole slide image (WSI) level, while each whole slide image can be divided into thousands of small image patches for training. The dominant MIL approaches take fixed patch features as inputs to address computational constraints and ensure model stability. These features are commonly generated by encoders pre-trained on ImageNet, foundation encoders pre-trained on large datasets, or through self-supervised learning on local datasets. While the self-supervised encoder pre-training on the same dataset as downstream MIL tasks helps mitigate domain shift and generate better features, the bag-level labels are not utilized during the process, and the features of patches from different categories may cluster together, reducing classification performance on MIL tasks. Recently, pre-training with supervised contrastive learning (SupCon) has demonstrated superior performance compared to self-supervised contrastive learning and even end-to-end training on traditional image classification tasks. In this paper, we propose a novel encoder pre-training method for downstream MIL tasks called Weakly Supervised Contrastive Learning (WeakSupCon) that utilizes bag-level labels. In our method, we employ multi-task learning and define distinct contrastive learning losses for samples with different bag labels. Our experiments demonstrate that the features generated using WeakSupCon significantly enhance MIL classification performance compared to self-supervised approaches across three datasets.

Problem

• Addresses weakly supervised multiple instance learning with bag-level labels.
• Proposes WeakSupCon for encoder pre-training using bag-level labels.
• Improves MIL classification performance over self-supervised methods.

Innovation

• Utilizes bag-level labels for encoder pre-training
• Employs multi-task learning with distinct contrastive losses
• Enhances MIL classification performance across datasets