Learning Class Difficulty in Imbalanced Histopathology Segmentation via Dynamic Focal Attention

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kumari, Lakmali Nadeesha, Cheung, Sen-Ching Samson
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908965169790976
author Kumari, Lakmali Nadeesha
Cheung, Sen-Ching Samson
author_facet Kumari, Lakmali Nadeesha
Cheung, Sen-Ching Samson
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13479
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Class Difficulty in Imbalanced Histopathology Segmentation via Dynamic Focal Attention
Kumari, Lakmali Nadeesha
Cheung, Sen-Ching Samson
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Learning Class Difficulty in Imbalanced Histopathology Segmentation via Dynamic Focal Attention
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.13479