DMSANet: Dual Multi Scale Attention Network

TL;DR

DMSANet introduces a lightweight dual multi-scale attention module that enhances performance in image classification, detection, and segmentation tasks while reducing computational complexity compared to existing models.

Contribution

The paper presents a novel dual multi-scale attention module that is lightweight, improves accuracy, and can be easily integrated into various CNN architectures.

Findings

Achieves state-of-the-art performance on ImageNet classification.

Outperforms existing models in object detection and segmentation on MS COCO.

Reduces parameters while maintaining high accuracy.

Abstract

Attention mechanism of late has been quite popular in the computer vision community. A lot of work has been done to improve the performance of the network, although almost always it results in increased computational complexity. In this paper, we propose a new attention module that not only achieves the best performance but also has lesser parameters compared to most existing models. Our attention module can easily be integrated with other convolutional neural networks because of its lightweight nature. The proposed network named Dual Multi Scale Attention Network (DMSANet) is comprised of two parts: the first part is used to extract features at various scales and aggregate them, the second part uses spatial and channel attention modules in parallel to adaptively integrate local features with their global dependencies. We benchmark our network performance for Image Classification on ImageNet dataset, Object Detection and Instance Segmentation both on MS COCO dataset.