skip to main content
10.1145/3357384.3357918acmconferencesArticle/Chapter ViewAbstractPublication PagescikmConference Proceedingsconference-collections
research-article

Adversarial Domain Adaptation with Semantic Consistency for Cross-Domain Image Classification

Published: 03 November 2019 Publication History

Abstract

In the cross-domain image classification scenario, domain adaption aims to address the challenge of transferring the knowledge obtained from the source domain to the target domain that is regarded as similar but different from the source domain. To get more reliable domain invariant representations, recent methods start to consider class-level distribution alignment across the source and target domains by adaptively assigning pseudo target labels. However, these approaches are vulnerable to the error accumulation and hence unable to preserve cross-domain category consistency. Because the accuracy of pseudo labels cannot be guaranteed explicitly. In this paper, we propose Adversarial Domain Adaptation with Semantic Consistency (ADASC) model to align the discriminative features across domains progressively and effectively, via exploiting the class-level relations between domains. Specifically, to simultaneously alleviate the negative influence of the false pseudo-target labels and get the discriminative domain invariant features, we introduce an Adaptive Centroid Alignment (ACA) strategy and a Class Discriminative Constraint (CDC) step to complement each other iteratively and alternatively in an end-to-end framework. Extensive experiments are conducted on several unsupervised domain adaptation datasets, and the results show that ADASC outperforms the state-of-the-art methods.

References

[1]
Shai Ben-David, John Blitzer, Koby Crammer, Alex Kulesza, Fernando Pereira, and Jennifer Wortman Vaughan. 2010. A theory of learning from different domains. Machine learning, Vol. 79, 1--2 (2010), 151--175.
[2]
Zhangjie Cao, Mingsheng Long, Chao Huang, and Jianmin Wang. 2018. Transfer Adversarial Hashing for Hamming Space Retrieval. In AAAI .
[3]
Yaroslav Ganin and Victor Lempitsky. 2014. Unsupervised domain adaptation by backpropagation. In ICML .
[4]
Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Francc ois Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. JMLR, Vol. 17, 1 (2016), 2096--2030.
[5]
Muhammad Ghifary, W Bastiaan Kleijn, Mengjie Zhang, David Balduzzi, and Wen Li. 2016. Deep reconstruction-classification networks for unsupervised domain adaptation. In ECCV .
[6]
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In NIPS. 2672--2680.
[7]
Arthur Gretton, Karsten Borgwardt, Malte Rasch, Bernhard Schölkopf, and Alex J Smola. 2007. A kernel method for the two-sample-problem. In NIPS. 513--520.
[8]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.
[9]
Guangneng Hu, Yu Zhang, and Qiang Yang. 2018. CoNet: Collaborative Cross Networks for Cross-Domain Recommendation. In CIKM. ACM, 667--676.
[10]
Jonathan J. Hull. 2002. A database for handwritten text recognition research. IEEE Transactions on pattern analysis and machine intelligence, Vol. 16, 5 (2002), 550--554.
[11]
Issam Laradji and Reza Babanezhad. 2018. M-ADDA: Unsupervised Domain Adaptation with Deep Metric Learning. In ICML .
[12]
Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE, Vol. 86, 11 (1998), 2278--2324.
[13]
Yiyang Li, Guanyu Tao, Weinan Zhang, Yong Yu, and Jun Wang. 2017. Content Recommendation by Noise Contrastive Transfer Learning of Feature Representation. In CIKM. ACM, 1657--1665.
[14]
Mingsheng Long, Yue Cao, Jianmin Wang, and Michael I Jordan. 2015. Learning transferable features with deep adaptation networks. In ICML. 97--105.
[15]
Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Michael I Jordan. 2018. Conditional adversarial domain adaptation. In NIPS. 1640--1650.
[16]
Mingsheng Long, Han Zhu, Jianmin Wang, and Michael I Jordan. 2017. Deep transfer learning with joint adaptation networks. In ICML. 2208--2217.
[17]
Yong Luo, Tongliang Liu, Yonggang Wen, and Dacheng Tao. 2018. Online Heterogeneous Transfer Metric Learning. In IJCAI .
[18]
Yawei Luo, Liang Zheng, Tao Guan, Junqing Yu, and Yi Yang. 2019. Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation. In CVPR .
[19]
Zelun Luo, Yuliang Zou, Judy Hoffman, and Li F Fei-Fei. 2017. Label efficient learning of transferable representations acrosss domains and tasks. In NIPS. 165--177.
[20]
Saeid Motiian, Quinn Jones, Seyed Iranmanesh, and Gianfranco Doretto. 2017. Few-shot adversarial domain adaptation. In NIPS .
[21]
Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y Ng. 2011. Reading digits in natural images with unsupervised feature learning. In NIPS, Vol. 2011. 5.
[22]
Zhongyi Pei, Zhangjie Cao, Mingsheng Long, and Jianmin Wang. 2018. Multi-adversarial domain adaptation. In AAAI .
[23]
Kate Saenko, Brian Kulis, Mario Fritz, and Trevor Darrell. 2010. Adapting visual category models to new domains. In ECCV .
[24]
Kuniaki Saito, Yoshitaka Ushiku, and Tatsuya Harada. 2017. Asymmetric tri-training for unsupervised domain adaptation. In ICML . 2988--2997.
[25]
Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. In NIPS. 4077--4087.
[26]
Baochen Sun and Kate Saenko. 2016. Deep coral: Correlation alignment for deep domain adaptation. In ECCV. 443--450.
[27]
Eric Tzeng, Judy Hoffman, Trevor Darrell, and Kate Saenko. 2015. Simultaneous deep transfer across domains and tasks. In ICCV .
[28]
Eric Tzeng, Judy Hoffman, Kate Saenko, and Trevor Darrell. 2017. Adversarial discriminative domain adaptation. In CVPR .
[29]
Eric Tzeng, Judy Hoffman, Ning Zhang, Kate Saenko, and Trevor Darrell. 2014. Deep domain confusion: Maximizing for domain invariance. In arXiv preprint arXiv:1412.3474 .
[30]
Riccardo Volpi, Pietro Morerio, Silvio Savarese, and Vittorio Murino. 2018. Adversarial feature augmentation for unsupervised domain adaptation. In CVPR . 5495--5504.
[31]
Fangzhao Wu, Sixing Wu, Yongfeng Huang, Songfang Huang, and Yong Qin. 2016. Sentiment domain adaptation with multi-level contextual sentiment knowledge. In CIKM. ACM, 949--958.
[32]
Werner Zellinger, Thomas Grubinger, Edwin Lughofer, Thomas Natschl"ager, and Susanne Saminger-Platz. 2017. Central moment discrepancy (cmd) for domain-invariant representation learning. arXiv preprint arXiv:1702.08811 (2017).
[33]
Jing Zhang, Zewei Ding, Wanqing Li, and Philip Ogunbona. 2018a. Importance Weighted Adversarial Nets for Partial Domain Adaptation. In CVPR . 8156--8164.
[34]
Weichen Zhang, Wanli Ouyang, Wen Li, and Dong Xu. 2018b. Collaborative and adversarial network for unsupervised domain adaptation. In CVPR . 3801--3809.
[35]
Feng Zhu, Yan Wang, Chaochao Chen, Guanfeng Liu, Mehmet A Orgun, and Jia Wu. 2018. A Deep Framework for Cross-Domain and Cross-System Recommendations. In IJCAI . 3711--3717.
[36]
Guangtang Zhu, Hanfang Yang, Lan Lin, Guichun Zhou, and Xiangdong Zhou. 2015. An informative logistic regression for cross-domain image classification. In ICVS . 147--156.

Cited By

View all
  • (2023)Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances2023 IEEE International Conference on Robotics and Automation (ICRA)10.1109/ICRA48891.2023.10160416(11374-11381)Online publication date: 29-May-2023
  • (2023)Pseudo-labeling Integrating Centers and Samples with Consistent Selection Mechanism for Unsupervised Domain AdaptationInformation Sciences10.1016/j.ins.2023.01.109628(50-69)Online publication date: May-2023
  • (2022)A Federated Transfer Learning Framework Based on Heterogeneous Domain Adaptation for Students’ Grades ClassificationApplied Sciences10.3390/app12211071112:21(10711)Online publication date: 22-Oct-2022
  • Show More Cited By

Index Terms

  1. Adversarial Domain Adaptation with Semantic Consistency for Cross-Domain Image Classification

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Conferences
      CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge Management
      November 2019
      3373 pages
      ISBN:9781450369763
      DOI:10.1145/3357384
      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]

      Sponsors

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 03 November 2019

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. adversarial learning
      2. classification
      3. domain adaptation
      4. semantic consistency

      Qualifiers

      • Research-article

      Conference

      CIKM '19
      Sponsor:

      Acceptance Rates

      CIKM '19 Paper Acceptance Rate 202 of 1,031 submissions, 20%;
      Overall Acceptance Rate 1,861 of 8,427 submissions, 22%

      Upcoming Conference

      CIKM '25

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)11
      • Downloads (Last 6 weeks)0
      Reflects downloads up to 10 Feb 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2023)Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances2023 IEEE International Conference on Robotics and Automation (ICRA)10.1109/ICRA48891.2023.10160416(11374-11381)Online publication date: 29-May-2023
      • (2023)Pseudo-labeling Integrating Centers and Samples with Consistent Selection Mechanism for Unsupervised Domain AdaptationInformation Sciences10.1016/j.ins.2023.01.109628(50-69)Online publication date: May-2023
      • (2022)A Federated Transfer Learning Framework Based on Heterogeneous Domain Adaptation for Students’ Grades ClassificationApplied Sciences10.3390/app12211071112:21(10711)Online publication date: 22-Oct-2022
      • (2022)Domain adversarial tangent subspace alignment for explainable domain adaptationNeurocomputing10.1016/j.neucom.2022.07.074506(418-429)Online publication date: Sep-2022
      • (2022)Discriminative transfer feature learning based on robust-centersNeurocomputing10.1016/j.neucom.2022.05.042500(39-57)Online publication date: Aug-2022
      • (2022)Adapted human pose: monocular 3D human pose estimation with zero real 3D pose dataApplied Intelligence10.1007/s10489-022-03341-652:12(14491-14506)Online publication date: 8-Mar-2022
      • (2021)Knowledge Preserving and Distribution Alignment for Heterogeneous Domain AdaptationACM Transactions on Information Systems10.1145/346985640:1(1-29)Online publication date: 8-Sep-2021
      • (2021)NormaProceedings of the 30th ACM International Conference on Information & Knowledge Management10.1145/3459637.3482458(833-843)Online publication date: 26-Oct-2021
      • (2021)Double Ensemble Soft Transfer Network for Unsupervised Domain AdaptationDatabase Systems for Advanced Applications10.1007/978-3-030-73197-7_34(516-532)Online publication date: 6-Apr-2021
      • (2021)Soft Labels Transfer with Discriminative Representations Learning for Unsupervised Domain AdaptationMachine Learning and Knowledge Discovery in Databases10.1007/978-3-030-67664-3_31(515-530)Online publication date: 25-Feb-2021

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media