AFENet: Attention-driven feature evolution network for precise polyp segmentation

doi:10.1016/j.bspc.2026.111306

AFENet: Attention-driven feature evolution network for precise polyp segmentation

2026-08-24

0

PRE

AI

DOI：10.1016/j.bspc.2026.111306

Original

Original request for help

Save

Abstract

En 中文

• Dual-stage feature evolution dynamically refines representations for polyp segmentation. • CaRL suppresses irrelevant activations and enhances discriminative feature learning. • AUR refines uncertainty estimation and reduces false negatives and positives. • Achieves superior performance on PolypGen, PSNBI2K, and PICCOLO datasets.

AFENet: Attention-driven feature evolution network for precise polyp segmentation

Abstract

Journal

Organization