LPD: Learnable Prototypes with Diversity Regularization for Weakly Supervised Histopathology Segmentation
This work addresses the challenge of reducing pixel-level labeling costs for histopathology segmentation, though it is incremental as it builds on existing prototype-based methods by integrating learning and regularization into a single stage.
The paper tackles the problem of weakly supervised semantic segmentation in histopathology, which suffers from inter-class homogeneity and intra-class heterogeneity, by proposing a cluster-free, one-stage learnable-prototype framework with diversity regularization, achieving state-of-the-art performance on BCSS-WSSS with improved mIoU and mDice metrics.
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.