research-article

Interpolation Normalization for Contrast Domain Generalization

Authors:

Qin ZhangAuthors Info & Claims

MM '23: Proceedings of the 31st ACM International Conference on Multimedia

Pages 2936 - 2945

https://doi.org/10.1145/3581783.3611841

Published: 27 October 2023 Publication History

Abstract

Domain generalization refers to the challenge of training a model from various source domains that can generalize well to unseen target domains. Contrastive learning is a promising solution that aims to learn domain-invariant representations by utilizing rich semantic relations among sample pairs from different domains. One simple approach is to bring positive sample pairs from different domains closer, while pushing negative pairs further apart. However, in this paper, we find that directly applying contrastive-based methods is not effective in domain generalization. To overcome this limitation, we propose to leverage a novel contrastive learning approach that promotes class-discriminative and class-balanced features from source domains. Essentially, clusters of sample representations from the same category are encouraged to cluster, while those from different categories are spread out, thus enhancing the model's generalization capability. Furthermore, most existing contrastive learning methods use batch normalization, which may prevent the model from learning domain-invariant features. Inspired by recent research on universal representations for neural networks, we propose a simple emulation of this mechanism by utilizing batch normalization layers to distinguish visual classes and formulating a way to combine them for domain generalization tasks. Our experiments demonstrate a significant improvement in classification accuracy over state-of-the-art techniques on popular domain generalization benchmarks, including Digits-DG, PACS, Office-Home and DomainNet.

References

[1]

Yang Bai and Weiqiang Wang. 2019. Acpnet: anchor-center based person network for human pose estimation and instance segmentation. In 2019 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 1072--1077.

[2]

Yogesh Balaji, Swami Sankaranarayanan, and Rama Chellappa. 2018. Metareg: Towards domain generalization using meta-regularization. NeurIPS, Vol. 31 (2018).

[3]

Konstantinos Bousmalis, George Trigeorgis, Nathan Silberman, Dilip Krishnan, and Dumitru Erhan. 2016. Domain separation networks. In Advances in neural information processing systems. 343--351.

[4]

Qi Cai, Yu Wang, Yingwei Pan, Ting Yao, and Tao Mei. 2020. Joint Contrastive Learning with Infinite Possibilities. In Proc. NeurIPS.

[5]

Fabio M Carlucci, Antonio D'Innocente, Silvia Bucci, Barbara Caputo, and Tatiana Tommasi. 2019. Domain generalization by solving jigsaw puzzles. In CVPR. 2229--2238.

[6]

Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, and Samuel Rota Bulo. 2017a. Autodial: Automatic domain alignment layers. In 2017 IEEE International Conference on Computer Vision (ICCV). IEEE, 5077--5085.

[7]

Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, and Samuel Rota Bulo. 2017b. Just dial: Domain alignment layers for unsupervised domain adaptation. In International Conference on Image Analysis and Processing. Springer, 357--369.

[8]

Prithvijit Chattopadhyay, Yogesh Balaji, and Judy Hoffman. 2020. Learning to balance specificity and invariance for in and out of domain generalization. In ECCV. 301--318.

[9]

Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proc. ICML, Vol. 119. 1597--1607.

[10]

Gratianus Wesley Putra Data, Kirjon Ngu, David William Murray, and Victor Adrian Prisacariu. 2018. Interpolating convolutional neural networks using batch normalization. In Proceedings of the European Conference on Computer Vision (ECCV). 574--588.

[11]

Zhengming Ding and Yun Fu. 2017. Deep domain generalization with structured low-rank constraint. IEEE Transactions on Image Processing, Vol. 27, 1 (2017), 304--313.

[12]

Qi Dou, Daniel Coelho de Castro, Konstantinos Kamnitsas, and Ben Glocker. 2019. Domain generalization via model-agnostic learning of semantic features. In Advances in Neural Information Processing Systems. 6447--6458.

[13]

Muhammad Ghifary, W Bastiaan Kleijn, Mengjie Zhang, and David Balduzzi. 2015. Domain generalization for object recognition with multi-task autoencoders. In ICCV. 2551--2559.

[14]

Ishaan Gulrajani and David Lopez-Paz. 2021. In search of lost domain generalization. ICLR (2021).

[15]

Raia Hadsell, Sumit Chopra, and Yann LeCun. 2006. Dimensionality Reduction by Learning an Invariant Mapping. In Proc. CVPR. 1735--1742.

Digital Library

[16]

Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross B. Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In Proc. CVPR. 9726--9735.

[17]

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.

[18]

Yen-Chang Hsu, Yilin Shen, Hongxia Jin, and Zsolt Kira. 2020. Generalized odin: Detecting out-of-distribution image without learning from out-of-distribution data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10951--10960.

[19]

Zeyi Huang, Haohan Wang, Eric P Xing, and Dong Huang. 2020. Self-challenging improves cross-domain generalization. In ECCV. 124--140.

[20]

Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In International Conference on Machine Learning. 448--456.

Digital Library

[21]

Seogkyu Jeon, Kibeom Hong, Pilhyeon Lee, Jewook Lee, and Hyeran Byun. 2021. Feature stylization and domain-aware contrastive learning for domain generalization. In Proceedings of the 29th ACM International Conference on Multimedia. 22--31.

Digital Library

[22]

Aditya Khosla, Tinghui Zhou, Tomasz Malisiewicz, Alexei A Efros, and Antonio Torralba. 2012. Undoing the damage of dataset bias. In European Conference on Computer Vision. Springer, 158--171.

Digital Library

[23]

Daehee Kim, Youngjun Yoo, Seunghyun Park, Jinkyu Kim, and Jaekoo Lee. 2021. Selfreg: Self-supervised contrastive regularization for domain generalization. In ICCV. 9619--9628.

[24]

Sungyeon Kim, Dongwon Kim, Minsu Cho, and Suha Kwak. 2020. Proxy anchor loss for deep metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3238--3247.

[25]

Gregory Koch, Richard Zemel, and Ruslan Salakhutdinov. 2015. Siamese neural networks for one-shot image recognition. In ICML deep learning workshop, Vol. 2. Lille.

[26]

Da Li, Yongxin Yang, Yi-Zhe Song, and Timothy M Hospedales. 2017. Deeper, broader and artier domain generalization. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 5542--5550.

[27]

Da Li, Yongxin Yang, Yi-Zhe Song, and Timothy M Hospedales. 2018 e. Learning to generalize: Meta-learning for domain generalization. In AAAI.

[28]

Da Li, Jianshu Zhang, Yongxin Yang, Cong Liu, Yi-Zhe Song, and Timothy M Hospedales. 2019. Episodic training for domain generalization. In Proceedings of the IEEE International Conference on Computer Vision. 1446--1455.

[29]

Haoliang Li, Sinno Jialin Pan, Shiqi Wang, and Alex C Kot. 2018b. Domain generalization with adversarial feature learning. In CVPR. 5400--5409.

[30]

Shuang Li, Binhui Xie, Bin Zang, Chi Harold Liu, Xinjing Cheng, Ruigang Yang, and Guoren Wang. 2021. Semantic distribution-aware contrastive adaptation for semantic segmentation. arXiv preprint arXiv:2105.05013 (2021).

[31]

Ya Li, Mingming Gong, Xinmei Tian, Tongliang Liu, and Dacheng Tao. 2018a. Domain generalization via conditional invariant representations. In Thirty-Second AAAI Conference on Artificial Intelligence.

[32]

Ya Li, Xinmei Tian, Mingming Gong, Yajing Liu, Tongliang Liu, Kun Zhang, and Dacheng Tao. 2018c. Deep domain generalization via conditional invariant adversarial networks. In ECCV. 624--639.

[33]

Yanghao Li, Naiyan Wang, Jianping Shi, Xiaodi Hou, and Jiaying Liu. 2018d. Adaptive batch normalization for practical domain adaptation. Pattern Recognition, Vol. 80 (2018), 109--117.

[34]

Antonio Loquercio, Elia Kaufmann, René Ranftl, Alexey Dosovitskiy, Vladlen Koltun, and Davide Scaramuzza. 2019. Deep drone racing: From simulation to reality with domain randomization. IEEE Transactions on Robotics (2019).

[35]

Divyat Mahajan, Shruti Tople, and Amit Sharma. 2021. Domain generalization using causal matching. In ICML. 7313--7324.

[36]

Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, and Elisa Ricci. 2018a. Best sources forward: domain generalization through source-specific nets. In 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 1353--1357.

[37]

Massimiliano Mancini, Samuel Rota Bulo, Barbara Caputo, and Elisa Ricci. 2018b. Robust place categorization with deep domain generalization. IEEE Robotics and Automation Letters, Vol. 3, 3 (2018), 2093--2100.

[38]

Massimiliano Mancini, Samuel Rota Bulo, Barbara Caputo, and Elisa Ricci. 2019. Adagraph: Unifying predictive and continuous domain adaptation through graphs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6568--6577.

[39]

Massimiliano Mancini, Lorenzo Porzi, Samuel Rota Bulò, Barbara Caputo, and Elisa Ricci. 2018c. Boosting domain adaptation by discovering latent domains. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3771--3780.

[40]

Toshihiko Matsuura and Tatsuya Harada. 2020. Domain generalization using a mixture of multiple latent domains. In AAAI. 11749--11756.

[41]

Saeid Motiian, Marco Piccirilli, Donald A Adjeroh, and Gianfranco Doretto. 2017. Unified deep supervised domain adaptation and generalization. In ICCV. 5715--5725.

[42]

Hyeonseob Nam and Hyo-Eun Kim. 2018. Batch-instance normalization for adaptively style-invariant neural networks. Advances in Neural Information Processing Systems, Vol. 31 (2018).

[43]

Hyeonseob Nam, HyunJae Lee, Jongchan Park, Wonjun Yoon, and Donggeun Yoo. 2021. Reducing domain gap by reducing style bias. In CVPR. 8690--8699.

[44]

Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko, and Bo Wang. 2019. Moment matching for multi-source domain adaptation. In ICCV. 1406--1415.

[45]

Vihari Piratla, Praneeth Netrapalli, and Sunita Sarawagi. 2020. Efficient domain generalization via common-specific low-rank decomposition. In ICML. 7728--7738.

[46]

Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh, and Sridha Sridharan. 2019. Multi-component image translation for deep domain generalization. In 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 579--588.

[47]

Shiv Shankar, Vihari Piratla, Soumen Chakrabarti, Siddhartha Chaudhuri, Preethi Jyothi, and Sunita Sarawagi. 2018. Generalizing across domains via cross-gradient training. ICLR (2018).

[48]

Josh Tobin, Rachel Fong, Alex Ray, Jonas Schneider, Wojciech Zaremba, and Pieter Abbeel. 2017. Domain randomization for transferring deep neural networks from simulation to the real world. In 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE, 23--30.

Digital Library

[49]

Aäron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. CoRR, Vol. abs/1807.03748 (2018).

[50]

Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, and Sethuraman Panchanathan. 2017. Deep hashing network for unsupervised domain adaptation. In CVPR. 5018--5027.

[51]

Mengzhu Wang, Paul Li, Li Shen, Ye Wang, Shanshan Wang, Wei Wang, Xiang Zhang, Junyang Chen, and Zhigang Luo. 2022a. Informative pairs mining based adaptive metric learning for adversarial domain adaptation. Neural Networks, Vol. 151 (2022), 238--249.

Digital Library

[52]

Mengzhu Wang, Shanshan Wang, Wei Wang, Li Shen, Xiang Zhang, Long Lan, and Zhigang Luo. 2023. Reducing bi-level feature redundancy for unsupervised domain adaptation. Pattern Recognition, Vol. 137 (2023), 109319.

Digital Library

[53]

Mengzhu Wang, Wei Wang, Baopu Li, Xiang Zhang, Long Lan, Huibin Tan, Tianyi Liang, Wei Yu, and Zhigang Luo. 2021. Interbn: Channel fusion for adversarial unsupervised domain adaptation. In Proceedings of the 29th ACM international conference on multimedia. 3691--3700.

Digital Library

[54]

Mengzhu Wang, Jianlong Yuan, Qi Qian, Zhibin Wang, and Hao Li. 2022b. Implicit Semantic Augmentation for Distance Metric Learning in Domain Generalization. ACMMM (2022).

[55]

Shujun Wang, Lequan Yu, Caizi Li, Chi-Wing Fu, and Pheng-Ann Heng. 2020. Learning from extrinsic and intrinsic supervisions for domain generalization. In ECCV. 159--176.

[56]

Binhui Xie, Shuang Li, Mingjia Li, Chi Harold Liu, Gao Huang, and Guoren Wang. 2023. Sepico: Semantic-guided pixel contrast for domain adaptive semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).

[57]

Dongkuan Xu, Wei Cheng, Dongsheng Luo, Haifeng Chen, and Xiang Zhang. 2021a. Infogcl: Information-aware graph contrastive learning. Advances in Neural Information Processing Systems, Vol. 34 (2021), 30414--30425.

[58]

Qinwei Xu, Ruipeng Zhang, Ya Zhang, Yanfeng Wang, and Qi Tian. 2021b. A fourier-based framework for domain generalization. In CVPR. 14383--14392.

[59]

Fu-En Yang, Yuan-Chia Cheng, Zu-Yun Shiau, and Yu-Chiang Frank Wang. 2021. Adversarial Teacher-Student Representation Learning for Domain Generalization. NeurIPS, Vol. 34 (2021).

[60]

Xufeng Yao, Yang Bai, Xinyun Zhang, Yuechen Zhang, Qi Sun, Ran Chen, Ruiyu Li, and Bei Yu. 2022. PCL: Proxy-based Contrastive Learning for Domain Generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7097--7107.

[61]

Kaichao You, Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Michael I Jordan. 2019. Universal domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2720--2729.

[62]

Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph contrastive learning with augmentations. Advances in neural information processing systems, Vol. 33 (2020), 5812--5823.

[63]

Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. ICLR (2017).

[64]

Kaiyang Zhou, Yongxin Yang, Timothy Hospedales, and Tao Xiang. 2020a. Deep domain-adversarial image generation for domain generalisation. In Proceedings of the AAAI Conference on Artificial Intelligence. 13025--13032.

[65]

Kaiyang Zhou, Yongxin Yang, Timothy Hospedales, and Tao Xiang. 2020b. Learning to generate novel domains for domain generalization. In ECCV. 561--578.

[66]

Rui Zhu, Bingchen Zhao, Jingen Liu, Zhenglong Sun, and Chang Wen Chen. 2021. Improving contrastive learning by visualizing feature transformation. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 10306--10315.

Cited By

Wang MLiu JLuo GWang SWang WLan LWang YNie F(2025)Smooth-Guided Implicit Data Augmentation for Domain GeneralizationIEEE Transactions on Neural Networks and Learning Systems10.1109/TNNLS.2024.337743936:3(4984-4995)Online publication date: Mar-2025
https://doi.org/10.1109/TNNLS.2024.3377439
Wang MLiu YYuan JWang SWang ZWang W(2024)Inter-Class and Inter-Domain Semantic Augmentation for Domain GeneralizationIEEE Transactions on Image Processing10.1109/TIP.2024.335442033(1338-1347)Online publication date: 23-Jan-2024
https://dl.acm.org/doi/10.1109/TIP.2024.3354420
Zhang QZhao W(2024)EDFFF: Ensemble Distillation Framework based on Fourier Features2024 China Automation Congress (CAC)10.1109/CAC63892.2024.10864742(7131-7136)Online publication date: 1-Nov-2024
https://doi.org/10.1109/CAC63892.2024.10864742
Show More Cited By

Index Terms

Interpolation Normalization for Contrast Domain Generalization
1. Computer systems organization
  1. Dependable and fault-tolerant systems and networks
    1. Redundancy
  2. Embedded and cyber-physical systems
    1. Embedded systems
    2. Robotics
2. Networks
  1. Network properties
    1. Network reliability

Recommendations

Achieving domain generalization for underwater object detection by domain mixup and contrastive learning
Abstract
The performance of existing underwater object detection methods severely degrades when they face the domain shift caused by complicated underwater environments. Due to the limited domain diversity in collected data, deep detectors ...
Domain-Conditioned Normalization for Test-Time Domain Generalization
Computer Vision – ECCV 2022 Workshops
Abstract
Domain generalization aims to train a robust model on multiple source domains that generalizes well to unseen target domains. While considerable attention has focused on training domain generalizable models, a few recent studies have shifted the ...
Batch normalization embeddings for deep domain generalization
Highlights
- We propose to accumulate domain-specific batch normalization statistics accumulated on convolutional layers to map image samples into a latent space where ...
Graphical abstract

Display Omitted

Abstract
Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. Several methods train models from multiple datasets to extract domain-invariant features, hoping to generalize to ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

MM '23: Proceedings of the 31st ACM International Conference on Multimedia

October 2023

9913 pages

ISBN:9798400701085

DOI:10.1145/3581783

General Chairs:
Abdulmotaleb El Saddik
University of Ottawa, Canada & MBZUAI, UAE
,
Tao Mei
HiDream.ai, China
,
Rita Cucchiara
University of Modena and Reggio Emilia, Italy
,
Program Chairs:
Marco Bertini
University of Florence, Italy
,
Diana Patricia Tobon Vallejo
Unversidad de Medellin, Colombia
,
Pradeep K. Atrey
University at Albany, State University of New York, USA
,
M. Shamim Hossain
M. Shamim Hossain (King Saud University, KSA

Copyright © 2023 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 the author(s) 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].

Sponsors

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 27 October 2023

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Open Research Fund from Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)
Natural Science Foundation of Guangdong Province of China
National Natural Science Foundation

Conference

MM '23

Sponsor:

SIGMM

MM '23: The 31st ACM International Conference on Multimedia

October 29 - November 3, 2023

Ottawa ON, Canada

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
259
Total Downloads

Downloads (Last 12 months)107
Downloads (Last 6 weeks)10

Reflects downloads up to 05 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Wang MLiu JLuo GWang SWang WLan LWang YNie F(2025)Smooth-Guided Implicit Data Augmentation for Domain GeneralizationIEEE Transactions on Neural Networks and Learning Systems10.1109/TNNLS.2024.337743936:3(4984-4995)Online publication date: Mar-2025
https://doi.org/10.1109/TNNLS.2024.3377439
Wang MLiu YYuan JWang SWang ZWang W(2024)Inter-Class and Inter-Domain Semantic Augmentation for Domain GeneralizationIEEE Transactions on Image Processing10.1109/TIP.2024.335442033(1338-1347)Online publication date: 23-Jan-2024
https://dl.acm.org/doi/10.1109/TIP.2024.3354420
Zhang QZhao W(2024)EDFFF: Ensemble Distillation Framework based on Fourier Features2024 China Automation Congress (CAC)10.1109/CAC63892.2024.10864742(7131-7136)Online publication date: 1-Nov-2024
https://doi.org/10.1109/CAC63892.2024.10864742
Xu HShi CFan WChen Z(2024)Improving diversity and discriminability based implicit contrastive learning for unsupervised domain adaptationApplied Intelligence10.1007/s10489-024-05351-y54:20(10007-10017)Online publication date: 1-Aug-2024
https://dl.acm.org/doi/10.1007/s10489-024-05351-y

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.

Figures

Tables

Media

View Table of Conten