research-article

Unsupervised Domain Adaptive Semantic Segmentation Based on Improved DAFormer

Authors:

Jin-Chun PiaoAuthors Info & Claims

AIPR '22: Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition

Pages 443 - 448

https://doi.org/10.1145/3573942.3574046

Published: 16 May 2023 Publication History

AIPR '22: Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition

Unsupervised Domain Adaptive Semantic Segmentation Based on Improved DAFormer

Pages 443 - 448

Abstract
References

Abstract

To overcome the intensive of manual labeling tasks at the pixel level required for semantic segmentation under traditional supervised learning, an Unsupervised Domain Adaptive for Semantic Segmentation (UDASS) method based on DAFormer improved model is proposed. This model adapted the Max Mean Discrepancy (MMD) method in the regenerated Hilbert space to help the alignment of the feature distribution, the soft paste strategy to retain the partially covered image blocks to help the model to accelerate convergence, the non-convex consistency regularization at the output level to enhance the robustness of the network, and the spatial pyramid pooling framework and the decoder with large window attention collaboration to improve its consistency. The proposed method was evaluated on the public dataset, and obtained the of 2.4% mIoU improvement in GTA5-to-Cityscapes and 1.1% mIoU in SYSTHIA-to-Cityscapes, respectively, which proved that this method was effective for DAFormer improvement.

References

[1]

Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 3431-3440.

[2]

Xiao T, Liu Y, Zhou B, Unified perceptual parsing for scene understanding[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 418-434.

[3]

Zhao H, Shi J, Qi X, Pyramid scene parsing network[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2881-2890.

[4]

Chen L C, Papandreou G, Kokkinos I, Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 40(4): 834-848.

[5]

Sakaridis C, Dai D, Van Gool L. ACDC: The adverse conditions dataset with correspondences for semantic driving scene understanding[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 10765-10775.

[6]

Cordts M, Omran M, Ramos S, The cityscapes dataset for semantic urban scene understanding[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 3213-3223.

[7]

Saleh F S, Aliakbarian M S, Salzmann M, Effective use of synthetic data for urban scene semantic segmentation[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 84-100.

[8]

Ettedgui S, Abu-Hussein S, Giryes R. ProCST: Boosting Semantic Segmentation using Progressive Cyclic Style-Transfer[J]. arXiv preprint arXiv:2204.11891, 2022.

[9]

Richter S R, Vineet V, Roth S, Playing for data: Ground truth from computer games[C]//European conference on computer vision. Springer, Cham, 2016: 102-118.

[10]

Ros G, Sellart L, Materzynska J, The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 3234-3243.

[11]

Gao L, Zhang J, Zhang L, Dsp: Dual soft-paste for unsupervised domain adaptive semantic segmentation[C]//Proceedings of the 29th ACM International Conference on Multimedia. 2021: 2825-2833.

[12]

Tsai Y H, Hung W C, Schulter S, Learning to adapt structured output space for semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7472-7481.

[13]

Cheng Y, Wei F, Bao J, Dual path learning for domain adaptation of semantic segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 9082-9091.

[14]

Zhang P, Zhang B, Zhang T, Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021: 12414-12424.

[15]

Zou Y, Yu Z, Kumar B V K, Unsupervised domain adaptation for semantic segmentation via class-balanced self-training[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 289-305.

[16]

Hoyer L, Dai D, Van Gool L. Daformer: Improving network architectures and training strategies for domain-adaptive semantic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 9924-9935.

[17]

He K, Zhang X, Ren S, Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.

[18]

Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.

[19]

Chen R, Rong Y, Guo S, Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation[J]. arXiv preprint arXiv:2203.07988, 2022.

[20]

Liu Z, Mao H, Wu C Y, A convnet for the 2020s[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 11976-11986.

[21]

Liu Z, Lin Y, Cao Y, Swin transformer: Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 10012-10022.

[22]

Yan H, Zhang C, Wu M. Lawin transformer: Improving semantic segmentation transformer with multi-scale representations via large window attention[J]. arXiv preprint arXiv:2201.01615, 2022.

[23]

Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]//International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015: 234-241.

[24]

Fu J, Liu J, Tian H, Dual attention network for scene segmentation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 3146-3154.

[25]

Zheng Z, Yang Y. Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation[J]. International Journal of Computer Vision, 2021, 129(4): 1106-1120.

Digital Library

[26]

Zhang P, Zhang B, Zhang T, Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021: 12414-12424.

[27]

Guo X, Yang C, Li B, Metacorrection: Domain-aware meta loss correction for unsupervised domain adaptation in semantic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 3927-3936.

[28]

Araslanov N, Roth S. Self-supervised augmentation consistency for adapting semantic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 15384-15394.

[29]

Tranheden W, Olsson V, Pinto J, Dacs: Domain adaptation via cross-domain mixed sampling[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2021: 1379-1389.

[30]

Xie E, Wang W, Yu Z, SegFormer: Simple and efficient design for semantic segmentation with transformers[J]. Advances in Neural Information Processing Systems, 2021, 34: 12077-12090.

[31]

Contributors M M S. OpenMMLab Semantic Segmentation Toolbox and Benchmark[J]. 2020.

Cited By

Hu HPiao J(2023)Semantic Segmentation of Urban Street Scenes Based on Prototype Learning and Neighborhood Attention2023 5th International Conference on Robotics and Computer Vision (ICRCV)10.1109/ICRCV59470.2023.10329050(114-118)Online publication date: 15-Sep-2023
https://doi.org/10.1109/ICRCV59470.2023.10329050

Index Terms

Unsupervised Domain Adaptive Semantic Segmentation Based on Improved DAFormer
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Image segmentation

Recommendations

Semi-supervised Domain Adaptive Medical Image Segmentation Through Consistency Regularized Disentangled Contrastive Learning
Medical Image Computing and Computer Assisted Intervention – MICCAI 2023
Abstract
Although unsupervised domain adaptation (UDA) is a promising direction to alleviate domain shift, they fall short of their supervised counterparts. In this work, we investigate relatively less explored semi-supervised domain adaptation (SSDA) for ...
Unsupervised Domain Adaptive Point Cloud Semantic Segmentation
Pattern Recognition
Abstract
Domain adaptation for point cloud semantic segmentation is important since manually labeling point cloud datasets for each domain are expensive and time-consuming. In this paper, in order to transfer prior knowledge from the labeled source domain ...
Noise-robust consistency regularization for semi-supervised semantic segmentation
Abstract
The essential of semi-supervised semantic segmentation (SSSS) is to learn more helpful information from unlabeled data, which can be achieved by assigning adequate quality pseudo-labels or managing noisy pseudo-labels during training. However, ...
Highlights
- The first work revisiting semi-supervised semantic segmentation from a robust learning view.
- Three novel noise-robust techniques for semi-supervised semantic segmentation.
- A novel semi-supervised semantic segmentation approach with ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

AIPR '22: Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition

September 2022

1221 pages

ISBN:9781450396899

DOI:10.1145/3573942

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 16 May 2023

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

Conference

AIPR 2022

AIPR 2022: 2022 5th International Conference on Artificial Intelligence and Pattern Recognition

September 23 - 25, 2022

Xiamen, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
77
Total Downloads

Downloads (Last 12 months)32
Downloads (Last 6 weeks)8

Reflects downloads up to 01 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Hu HPiao J(2023)Semantic Segmentation of Urban Street Scenes Based on Prototype Learning and Neighborhood Attention2023 5th International Conference on Robotics and Computer Vision (ICRCV)10.1109/ICRCV59470.2023.10329050(114-118)Online publication date: 15-Sep-2023
https://doi.org/10.1109/ICRCV59470.2023.10329050

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Table of Conten