Squeeze-and-Attention Networks for Semantic Segmentation

09/08/2019
by   Zilong Zhong, et al.
45

Squeeze-and-excitation (SE) module enhances the representational power of convolution layers by adaptively re-calibrating channel-wise feature responses. However, the limitation of SE in terms of attention characterization lies in the loss of spatial information cues, making it less well suited for perception tasks with very high spatial inter-dependencies such as semantic segmentation. In this paper, we propose a novel squeeze-and-attention network (SANet) architecture that leverages a simple but effective squeeze-and-attention (SA) module to account for two distinctive characteristics of segmentation: i) pixel-group attention, and ii) pixel-wise prediction. Specifically, the proposed SA modules impose pixel-group attention on conventional convolution by introducing an 'attention' convolutional channel, thus taking into account spatial-channel inter-dependencies in an efficient manner. The final segmentation results are produced by merging outputs from four hierarchical stages of a SANet to integrate multi-scale contexts for obtaining enhanced pixel-wise prediction. Empirical experiments using two challenging public datasets validate the effectiveness of the proposed SANets, which achieved 83.2 mIoU of 54.4

READ FULL TEXT

page 1

page 4

page 5

page 7

page 8

research
09/09/2018

Dual Attention Network for Scene Segmentation

In this paper, we address the scene segmentation task by capturing rich ...
research
01/08/2021

Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction

Multi-scale representations deeply learned via convolutional neural netw...
research
11/26/2022

Rethinking Alignment and Uniformity in Unsupervised Image Semantic Segmentation

Unsupervised image semantic segmentation(UISS) aims to match low-level v...
research
07/02/2021

Polarized Self-Attention: Towards High-quality Pixel-wise Regression

Pixel-wise regression is probably the most common problem in fine-graine...
research
12/24/2021

Realtime Global Attention Network for Semantic Segmentation

In this paper, we proposed an end-to-end realtime global attention neura...
research
04/27/2020

Distance Guided Channel Weighting for Semantic Segmentation

Recent works have achieved great success in improving the performance of...
research
09/25/2021

ReCal-Net: Joint Region-Channel-Wise Calibrated Network for Semantic Segmentation in Cataract Surgery Videos

Semantic segmentation in surgical videos is a prerequisite for a broad r...

Please sign up or login with your details

Forgot password? Click here to reset