DMSANet: Dual Multi Scale Attention Network

by   abhinavsagar, et al.

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.


page 1

page 2

page 3

page 4


Dual Attention Network for Scene Segmentation

In this paper, we address the scene segmentation task by capturing rich ...

CAT: Learning to Collaborate Channel and Spatial Attention from Multi-Information Fusion

Channel and spatial attention mechanism has proven to provide an evident...

NSANet: Noise Seeking Attention Network

LiDAR (Light Detection and Ranging) technology has remained popular in c...

DPANET:Dual Pooling Attention Network for Semantic Segmentation

Image segmentation is a historic and significant computer vision task. W...

BARNet: Bilinear Attention Network with Adaptive Receptive Field for Surgical Instrument Segmentation

Surgical instrument segmentation is extremely important for computer-ass...

MixDehazeNet : Mix Structure Block For Image Dehazing Network

Image dehazing is a typical task in the low-level vision field. Previous...

An attention mechanism based convolutional network for satellite precipitation downscaling over China

Precipitation is a key part of hydrological circulation and is a sensiti...

Code Repositories


Code for the paper DMSANet: Dual Multi Scale Attention Network

view repo

Please sign up or login with your details

Forgot password? Click here to reset