UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation

TL;DR

UACANet introduces an uncertainty-aware attention mechanism in a modified U-Net architecture, significantly improving polyp segmentation accuracy by effectively modeling uncertain regions, achieving state-of-the-art results on multiple benchmarks.

Contribution

The paper presents a novel uncertainty augmented context attention mechanism integrated into a U-Net based network for enhanced polyp segmentation.

Findings

Achieved 76.6% mean Dice on ETIS dataset, a 13.8% improvement over previous methods.

Outperformed existing methods on five benchmark datasets.

Demonstrated the effectiveness of modeling uncertain regions in segmentation tasks.

Abstract

We propose Uncertainty Augmented Context Attention network (UACANet) for polyp segmentation which consider a uncertain area of the saliency map. We construct a modified version of U-Net shape network with additional encoder and decoder and compute a saliency map in each bottom-up stream prediction module and propagate to the next prediction module. In each prediction module, previously predicted saliency map is utilized to compute foreground, background and uncertain area map and we aggregate the feature map with three area maps for each representation. Then we compute the relation between each representation and each pixel in the feature map. We conduct experiments on five popular polyp segmentation benchmarks, Kvasir, CVC-ClinicDB, ETIS, CVC-ColonDB and CVC-300, and achieve state-of-the-art performance. Especially, we achieve 76.6% mean Dice on ETIS dataset which is 13.8% improvement compared to the previous state-of-the-art method. Source code is publicly available at https://github.com/plemeri/UACANet