ABSTRACT
In recent years, deep domain adaptation (DA) technology has been widely used in cross-domain hyperspectral image (HSI) classification problems. However, most existing deep DA algorithms aim to align the distributions of domains while ignoring sample information. In order to solve this problem, this paper proposes a new instance similarity-based adversarial domain adaptation (ISADA) method. ISADA combines the ideas of adversarial learning and contrastive learning to reduce domain shift from two aspects: marginal distribution and class conditional probability distribution. The adversarial training of generator and discriminator is used to reduce the difference in marginal distribution between domains, and the multi-instance contrastive (MIC) loss is used to align the category distribution between domains. Experimental results on two cross-domain HSI classification tasks show that our proposed ISADA method outperforms some existing deep DA methods.
- Xavier Glorot, Antoine Bordes, and Yoshua Bengio. 2011. Deep Sparse Rectifier Neural Networks. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics(Proceedings of Machine Learning Research, Vol. 15). PMLR, 315–323.Google Scholar
- Yi Huang, Jiangtao Peng, Na Chen, 2023. Cross-scene wetland mapping on hyperspectral remote sensing images using adversarial domain adaptation network. ISPRS J. Photogramm. Remote Sens. 203 (2023), 37–54.Google ScholarCross Ref
- Yi Huang, Jiangtao Peng, Weiwei Sun, 2022. Two-Branch Attention Adversarial Domain Adaptation Network for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens. 60 (2022), 22236204.Google ScholarCross Ref
- Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In ICML.Google ScholarDigital Library
- Mingsheng Long, Yue Cao, Zhangjie Cao, 2019. Transferable Representation Learning with Deep Adaptation Networks. IEEE Trans. Pattern Anal. Machine Intell. 41, 12 (2019), 3071–3085.Google ScholarCross Ref
- Iveta Mrazova and Marek Kukacka. 2013. Image Classification with Growing Neural Networks. International Journal of Computer Theory and Engineering (2013), 422–427.Google ScholarCross Ref
- Praveen S. Muthukumarana and Achala Chathuranga Aponso. 2020. A Review on Deep Learning Based Image Classification of Plant Diseases.Google Scholar
- Sinno Jialin Pan and Qiang Yang. 2009. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22, 10 (2009), 1345–1359.Google ScholarDigital Library
- Jiangtao Peng, Yi Huang, Weiwei Sun, 2022. Domain Adaptation in Remote Sensing Image Classification: A Survey. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 15 (2022), 9842–9859.Google ScholarCross Ref
- Astuti Sharma, Subrahmanya Kalluri, and Manmohan Chandraker. 2021. Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation. CVPR, 5357–5367.Google Scholar
- Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. J. Mach. Learn. Res. 15, 1 (jan 2014), 1929––1958.Google ScholarDigital Library
- T. Tran, Caleb Vununu, Sukhrob Atoev, Suk-Hwan Lee, and Ki-Ryong Kwon. 2018. Leukemia Blood Cell Image Classification Using Convolutional Neural Network. International journal of computer theory and engineering 10 (04 2018), 54–58.Google Scholar
- Devis Tuia, Claudio Persello, and Lorenzo Bruzzone. 2016. Domain adaptation for the classification of remote sensing data: An overview of recent advances. IEEE Geosci. Remote Sens. Mag. 4, 2 (2016), 41–57.Google ScholarCross Ref
- Eric Tzeng, Judy Hoffman, Kate Saenko, 2017. Adversarial Discriminative Domain Adaptation. In CVPR. 2962–2971.Google Scholar
- Chaohui Yu, Jindong Wang, Yiqiang Chen, 2019. Transfer Learning with Dynamic Adversarial Adaptation Network. In ICDM. 778–786.Google Scholar
- Yuxiang Zhang, Wei Li, Mengmeng Zhang, 2021. Topological Structure and Semantic Information Transfer Network for Cross-Scene Hyperspectral Image Classification. IEEE Trans. Neur. Netw. Learn. Syst. (2021).Google Scholar
- Yongchun Zhu, Fuzhen Zhuang, Jindong Wang, 2021. Deep Subdomain Adaptation Network for Image Classification. IEEE Trans. Neur. Netw. Learn. Syst. 32, 4 (2021), 1713–1722.Google ScholarCross Ref
Index Terms
- Instance Similarity-based Adversarial Domain Adaptation Network for Hyperspectral Image Classification
Recommendations
Adversarial domain adaptation using contrastive learning
AbstractIn recent research, problems with biased datasets or domain shift have presented challenges to the practical applications of deep learning methods. In this paper, we propose a simple method using adversarial learning combined with contrastive ...
Highlights- We investigated an unsupervised domain adaptation task.
- Combining adversarial and contrastive learning can address the domain-shift issue.
- The proposed method is practical and implementation is very simple.
Unsupervised domain adaptation with adversarial distribution adaptation network
AbstractAdversarial domain adaptation is a powerful approach to transfer the knowledge of the label-rich source domain to the label-scarce target domain by mitigating domain shifts across distributions. Existing domain adaptation methods align either the ...
Deep Domain Adaptation Hashing with Adversarial Learning
SIGIR '18: The 41st International ACM SIGIR Conference on Research & Development in Information RetrievalThe recent advances in deep neural networks have demonstrated high capability in a wide variety of scenarios. Nevertheless, fine-tuning deep models in a new domain still requires a significant amount of labeled data despite expensive labeling efforts. A ...
Comments