EPSANet: An Efficient Pyramid Split Attention Block on Convolutional Neural Network

by   Hu Zhang, et al.

Recently, it has been demonstrated that the performance of a deep convolutional neural network can be effectively improved by embedding an attention module into it. In this work, a novel lightweight and effective attention method named Pyramid Split Attention (PSA) module is proposed. By replacing the 3x3 convolution with the PSA module in the bottleneck blocks of the ResNet, a novel representational block named Efficient Pyramid Split Attention (EPSA) is obtained. The EPSA block can be easily added as a plug-and-play component into a well-established backbone network, and significant improvements on model performance can be achieved. Hence, a simple and efficient backbone architecture named EPSANet is developed in this work by stacking these ResNet-style EPSA blocks. Correspondingly, a stronger multi-scale representation ability can be offered by the proposed EPSANet for various computer vision tasks including but not limited to, image classification, object detection, instance segmentation, etc. Without bells and whistles, the performance of the proposed EPSANet outperforms most of the state-of-the-art channel attention methods. As compared to the SENet-50, the Top-1 accuracy is improved by 1.93 +2.7 box AP for object detection and an improvement of +1.7 mask AP for instance segmentation by using the Mask-RCNN on MS-COCO dataset are obtained. Our source code is available at:https://github.com/murufeng/EPSANet.


page 1

page 2

page 3

page 4


HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network

This paper addresses representational block named Hierarchical-Split Blo...

ResNeSt: Split-Attention Networks

While image classification models have recently continued to advance, mo...

Bottleneck Transformers for Visual Recognition

We present BoTNet, a conceptually simple yet powerful backbone architect...

TreeNet: A lightweight One-Shot Aggregation Convolutional Network

The architecture of deep convolutional networks (CNNs) has evolved for y...

AutoBSS: An Efficient Algorithm for Block Stacking Style Search

Neural network architecture design mostly focuses on the new convolution...

A novel Region of Interest Extraction Layer for Instance Segmentation

Given the wide diffusion of deep neural network architectures for comput...

Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution

This paper proposes a novel module called middle spectrum grouped convol...

Please sign up or login with your details

Forgot password? Click here to reset