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

TL;DR

This paper tackles weakly supervised semantic segmentation in histopathology by addressing CAM-induced region shrinkage and high intra-class variability with a cluster-free, one-stage framework of learnable prototypes. It introduces Prototype Constructor, Mask Refiner, and a Novel Prototype Diversity Regularizer to encourage complementary, non-overlapping tissue-pattern attention, enabling end-to-end training. The approach achieves state-of-the-art results on BCSS-WSSS, notably with 10 prototypes, and ablations demonstrate the necessity of diversity regularization for maximizing coverage. The work offers an efficient, scalable solution that yields sharper segmentation boundaries and more robust region localization in histopathology images.

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.

Figures (3)

• Figure 1: Overview of the LDP framework.Prototype Constructor (blue) produces learnable prototypes generating class CAMs. Mask Refiner (orange, top) fuses CAMs into pseudo masks and performs FG/BG contrastive alignment. Prototype Diversity Regularizer (green, bottom) encourages prototypes to capture distinct tissue patterns.
• Figure 2: Visualization of segmentation masks of different model on the BCSS-WSSS dataset
• Figure 3: Activation heatmaps across segmentation classes for clustering-based and LDP's prototype on BCSS-WSSS, each configured with 3 prototypes