Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces Dynamic Focal Attention (DFA), a novel attention mechanism for handling class imbalance in histopathology image segmentation. DFA learns class-specific difficulty by introducing a learnable per-class bias to attention logits within a query-based mask decoder, effectively reweighting representations before prediction. Experiments on three histopathology datasets (BDSA, BCSS, CRAG) demonstrate that DFA achieves improved segmentation performance compared to frequency-based reweighting and matches or exceeds a difficulty-aware baseline.
Forget static loss reweighting: learning class difficulty directly within attention layers beats the state-of-the-art for imbalanced histopathology segmentation.
Semantic segmentation of histopathology images under class imbalance is typically addressed through frequency-based loss reweighting, which implicitly assumes that rare classes are difficult. However, true difficulty also arises from morphological variability, boundary ambiguity, and contextual similarity-factors that frequency cannot capture. We propose Dynamic Focal Attention (DFA), a simple and efficient mechanism that learns class-specific difficulty directly within the cross-attention of query-based mask decoders. DFA introduces a learnable per-class bias to attention logits, enabling representation-level reweighting prior to prediction rather than gradient-level reweighting after prediction. Initialised from a log-frequency prior to prevent gradient starvation, the bias is optimised end-to-end, allowing the model to adaptively capture difficulty signals through training, effectively unifying frequency-based and difficulty-aware approaches under a common attention-bias framework. On three histopathology benchmarks (BDSA, BCSS, CRAG), DFA consistently improves Dice and IoU, matching or exceeding a difficulty-aware baseline without a separate estimator or additional training stage. These results demonstrate that encoding class difficulty at the representation level provides a principled alternative to conventional loss reweighting for imbalanced segmentation.