Saved in:
Bibliographic Details
Main Authors: Xu, Guoan, Huang, Wenfeng, Wu, Tao, Chen, Ligeng, Jia, Wenjing, Gao, Guangwei, Zhu, Xiatian, Perry, Stuart
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.05699
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909284475863040
author Xu, Guoan
Huang, Wenfeng
Wu, Tao
Chen, Ligeng
Jia, Wenjing
Gao, Guangwei
Zhu, Xiatian
Perry, Stuart
author_facet Xu, Guoan
Huang, Wenfeng
Wu, Tao
Chen, Ligeng
Jia, Wenjing
Gao, Guangwei
Zhu, Xiatian
Perry, Stuart
contents Semantic segmentation involves assigning a specific category to each pixel in an image. While Vision Transformer-based models have made significant progress, current semantic segmentation methods often struggle with precise predictions in localized areas like object boundaries. To tackle this challenge, we introduce a new semantic segmentation architecture, ``MacFormer'', which features two key components. Firstly, using learnable agent tokens, a Mutual Agent Cross-Attention (MACA) mechanism effectively facilitates the bidirectional integration of features across encoder and decoder layers. This enables better preservation of low-level features, such as elementary edges, during decoding. Secondly, a Frequency Enhancement Module (FEM) in the decoder leverages high-frequency and low-frequency components to boost features in the frequency domain, benefiting object boundaries with minimal computational complexity increase. MacFormer is demonstrated to be compatible with various network architectures and outperforms existing methods in both accuracy and efficiency on benchmark datasets ADE20K and Cityscapes under different computational constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2408_05699
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MacFormer: Semantic Segmentation with Fine Object Boundaries
Xu, Guoan
Huang, Wenfeng
Wu, Tao
Chen, Ligeng
Jia, Wenjing
Gao, Guangwei
Zhu, Xiatian
Perry, Stuart
Computer Vision and Pattern Recognition
Semantic segmentation involves assigning a specific category to each pixel in an image. While Vision Transformer-based models have made significant progress, current semantic segmentation methods often struggle with precise predictions in localized areas like object boundaries. To tackle this challenge, we introduce a new semantic segmentation architecture, ``MacFormer'', which features two key components. Firstly, using learnable agent tokens, a Mutual Agent Cross-Attention (MACA) mechanism effectively facilitates the bidirectional integration of features across encoder and decoder layers. This enables better preservation of low-level features, such as elementary edges, during decoding. Secondly, a Frequency Enhancement Module (FEM) in the decoder leverages high-frequency and low-frequency components to boost features in the frequency domain, benefiting object boundaries with minimal computational complexity increase. MacFormer is demonstrated to be compatible with various network architectures and outperforms existing methods in both accuracy and efficiency on benchmark datasets ADE20K and Cityscapes under different computational constraints.
title MacFormer: Semantic Segmentation with Fine Object Boundaries
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.05699