LPD: Learnable Prototypes with Diversity Regularization for Weakly Supervised Histopathology Segmentation

TL;DR

This paper introduces a novel one-stage learnable-prototype framework with diversity regularization for weakly supervised histopathology segmentation, improving coverage and boundary accuracy over prior clustering-based methods.

Contribution

It presents a cluster-free, end-to-end prototype learning approach that enhances intra-class heterogeneity coverage and simplifies the segmentation pipeline.

Findings

Achieves state-of-the-art performance on BCSS-WSSS dataset.

Produces sharper segmentation boundaries with fewer mislabels.

Demonstrates more diverse and comprehensive prototype coverage.

Abstract

Weakly supervised semantic segmentation (WSSS) in histopathology reduces pixel-level labeling by learning from image-level labels, but it is hindered by inter-class homogeneity, intra-class heterogeneity, and CAM-induced region shrinkage (global pooling-based class activation maps whose activations highlight only the most distinctive areas and miss nearby class regions). Recent works address these challenges by constructing a clustering prototype bank and then refining masks in a separate stage; however, such two-stage pipelines are costly, sensitive to hyperparameters, and decouple prototype discovery from segmentation learning, limiting their effectiveness and efficiency. We propose a cluster-free, one-stage learnable-prototype framework with diversity regularization to enhance morphological intra-class heterogeneity coverage. Our approach achieves state-of-the-art (SOTA) performance on BCSS-WSSS, outperforming prior methods in mIoU and mDice. Qualitative segmentation maps show sharper boundaries and fewer mislabels, and activation heatmaps further reveal that, compared with clustering-based prototypes, our learnable prototypes cover more diverse and complementary regions within each class, providing consistent qualitative evidence for their effectiveness.