DSNet: a simple yet efficient network with dual-stream attention for lesion segmentation

TL;DR

DSNet is an efficient lesion segmentation network combining Transformer and CNN components, utilizing dual-stream attention modules to improve accuracy while maintaining low complexity, outperforming state-of-the-art methods.

Contribution

Introduces a novel DSNet architecture with dual-stream attention modules that effectively fuse features for improved lesion segmentation performance.

Findings

Achieves state-of-the-art Dice and IoU scores on multiple datasets.

Maintains low model complexity and memory usage.

Outperforms existing methods in accuracy and efficiency.

Abstract

Lesion segmentation requires both speed and accuracy. In this paper, we propose a simple yet efficient network DSNet, which consists of a encoder based on Transformer and a convolutional neural network(CNN)-based distinct pyramid decoder containing three dual-stream attention (DSA) modules. Specifically, the DSA module fuses features from two adjacent levels through the false positive stream attention (FPSA) branch and the false negative stream attention (FNSA) branch to obtain features with diversified contextual information. We compare our method with various state-of-the-art (SOTA) lesion segmentation methods with several public datasets, including CVC-ClinicDB, Kvasir-SEG, and ISIC-2018 Task 1. The experimental results show that our method achieves SOTA performance in terms of mean Dice coefficient (mDice) and mean Intersection over Union (mIoU) with low model complexity and memory consumption.