CAA : Channelized Axial Attention for Semantic Segmentation

01/19/2021
by   Ye Huang, et al.
0

Self-attention and channel attention, modelling the semantic interdependencies in spatial and channel dimensions respectively, have recently been widely used for semantic segmentation. However, computing self-attention and channel attention separately and then fusing them directly can cause conflicting feature representations. In this paper, we propose the Channelized Axial Attention (CAA) to seamlessly integrate channel attention and axial attention with reduced computational complexity. After computing axial attention maps, we propose to channelize the intermediate results obtained from the transposed dot-product so that the channel importance of each axial representation is optimized across the whole receptive field. We further develop grouped vectorization, which allows our model to be run in the very limited GPU memory with a speed comparable with full vectorization. Comparative experiments conducted on multiple benchmark datasets, including Cityscapes, PASCAL Context and COCO-Stuff, demonstrate that our CAA not only requires much less computation resources but also outperforms the state-of-the-art segmentation models based on ResNet-101 on all tested datasets.

READ FULL TEXT

page 7

page 8

research
12/08/2021

Fully Attentional Network for Semantic Segmentation

Recent non-local self-attention methods have proven to be effective in c...
research
07/07/2020

Real-time Semantic Segmentation with Fast Attention

In deep CNN based models for semantic segmentation, high accuracy relies...
research
07/31/2019

Expectation-Maximization Attention Networks for Semantic Segmentation

Self-attention mechanism has been widely used for various tasks. It is d...
research
07/29/2019

Interlaced Sparse Self-Attention for Semantic Segmentation

In this paper, we present a so-called interlaced sparse self-attention a...
research
11/28/2022

FsaNet: Frequency Self-attention for Semantic Segmentation

Considering the spectral properties of images, we propose a new self-att...
research
07/10/2022

Self-attention on Multi-Shifted Windows for Scene Segmentation

Scene segmentation in images is a fundamental yet challenging problem in...
research
05/18/2021

Progressively Normalized Self-Attention Network for Video Polyp Segmentation

Existing video polyp segmentation (VPS) models typically employ convolut...

Please sign up or login with your details

Forgot password? Click here to reset