Cross Attention Network for Semantic Segmentation

07/25/2019
by   Mengyu Liu, et al.
0

In this paper, we address the semantic segmentation task with a deep network that combines contextual features and spatial information. The proposed Cross Attention Network is composed of two branches and a Feature Cross Attention (FCA) module. Specifically, a shallow branch is used to preserve low-level spatial information and a deep branch is employed to extract high-level contextual features. Then the FCA module is introduced to combine these two branches. Different from most existing attention mechanisms, the FCA module obtains spatial attention map and channel attention map from two branches separately, and then fuses them. The contextual features are used to provide global contextual guidance in fused feature maps, and spatial features are used to refine localizations. The proposed network outperforms other real-time methods with improved speed on the Cityscapes and CamVid datasets with lightweight backbones, and achieves state-of-the-art performance with a deep backbone.

READ FULL TEXT
research
05/25/2018

Pyramid Attention Network for Semantic Segmentation

A Pyramid Attention Network(PAN) is proposed to exploit the impact of gl...
research
11/21/2022

SLLEN: Semantic-aware Low-light Image Enhancement Network

How to effectively explore semantic feature is vital for low-light image...
research
10/11/2022

DPANET:Dual Pooling Attention Network for Semantic Segmentation

Image segmentation is a historic and significant computer vision task. W...
research
05/18/2023

XFormer: Fast and Accurate Monocular 3D Body Capture

We present XFormer, a novel human mesh and motion capture method that ac...
research
08/04/2021

Multi-Branch with Attention Network for Hand-Based Person Recognition

In this paper, we propose a novel hand-based person recognition method f...
research
09/02/2021

FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation

Real-time semantic segmentation, which can be visually understood as the...
research
03/26/2020

Fastidious Attention Network for Navel Orange Segmentation

Deep learning achieves excellent performance in many domains, so we not ...

Please sign up or login with your details

Forgot password? Click here to reset