Multi-Layer Dense Attention Decoder for Polyp Segmentation

TL;DR

This paper introduces a novel multi-layer dense attention decoder with a Dense Attention Gate for improved polyp segmentation, addressing local relation learning and feature aggregation issues in vision Transformer-based models.

Contribution

It proposes a hierarchical dense decoder with a Dense Attention Gate module, enhancing local feature relations and semantic feature aggregation for polyp segmentation.

Findings

Achieves state-of-the-art performance on five polyp datasets.

Outperforms nine competing models on four datasets.

Demonstrates robustness across diverse polyp variations.

Abstract

Detecting and segmenting polyps is crucial for expediting the diagnosis of colon cancer. This is a challenging task due to the large variations of polyps in color, texture, and lighting conditions, along with subtle differences between the polyp and its surrounding area. Recently, vision Transformers have shown robust abilities in modeling global context for polyp segmentation. However, they face two major limitations: the inability to learn local relations among multi-level layers and inadequate feature aggregation in the decoder. To address these issues, we propose a novel decoder architecture aimed at hierarchically aggregating locally enhanced multi-level dense features. Specifically, we introduce a novel module named Dense Attention Gate (DAG), which adaptively fuses all previous layers' features to establish local feature relations among all layers. Furthermore, we propose a novel nested decoder architecture that hierarchically aggregates decoder features, thereby enhancing semantic features. We incorporate our novel dense decoder with the PVT backbone network and conduct evaluations on five polyp segmentation datasets: Kvasir, CVC-300, CVC-ColonDB, CVC-ClinicDB, and ETIS. Our experiments and comparisons with nine competing segmentation models demonstrate that the proposed architecture achieves state-of-the-art performance and outperforms the previous models on four datasets. The source code is available at: https://github.com/krushi1992/Dense-Decoder.