journal article·2021-06-06Open access

P-Norm Attention Deep CORAL: Extending Correlation Alignment Using Attention and the P-Norm Loss Function

Zhi-Yong Wang, Dae-Ki Kang

Applied Sciences· Volume 11· Issue 11

Abstract

CORrelation ALignment (CORAL) is an unsupervised domain adaptation method that uses a linear transformation to align the covariances of source and target domains. Deep CORAL extends CORAL with a nonlinear transformation using a deep neural network and adds CORAL loss as a part of the total loss to align the covariances of source and target domains. However, there are still two problems to be solved in Deep CORAL: features extracted from AlexNet are not always a good representation of the original data, as well as joint training combined with both the classification and CORAL loss may not be efficient enough to align the distribution of the source and target domain. In this paper, we proposed two strategies: attention to improve the quality of feature maps and the p-norm loss function to align the distribution of the source and target features, further reducing the offset caused by the classification loss function. Experiments on the Office-31 dataset indicate that our proposed methodologies improved Deep CORAL in terms of performance.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Domain Adaptation and Few-Shot Learning · Multimodal Machine Learning Applications · Human Pose and Action Recognition

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Computer Software, Weifang University of Science and Technology, Shouguang 262700, China

Department of Computer Engineering, Dongseo University, Busan 47011, Korea

Funding

National Research Foundation of Korea

References (17)

Show source-provided references
1. He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 13–16). Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.123 ↗
2. Mastering the Game of Go with Deep Neural Networks and Tree Search10.1038/nature16961 ↗
3. Mastering Atari, Go, chess and shogi by planning with a learned model10.1038/s41586-020-03051-4 ↗
4. Hoffman, J., Rodner, E., Donahue, J., Saenko, K., and Darrell, T. (2013, January 2–4). Efficient Learning of Domain Invariant Image Representations. Proceedings of the 1st International Conference on Learning Representations (ICLR), Scottsdale, Arizona.
5. Luo, Y., Zheng, L., Guan, T., Yu, J., and Yang, Y. (2019, January 16–20). Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00261 ↗
6. Zhao, S., Yue, X., Zhang, S., Li, B., Zhao, H., Wu, B., Krishna, R., Gonzalez, J.E., Sangiovanni-Vincentelli, A.L., and Seshia, S.A. (2020). A Review of Single-Source Deep Unsupervised Visual Domain Adaptation. IEEE Trans. Neural. Netw. Learn. Syst.
7. Sun, B., Feng, J., and Saenko, K. (2015). Return of frustratingly easy domain adaptation. arXiv.10.1609/aaai.v30i1.10306 ↗
8. Sun, B., and Saenko, K. (2016). Deep Coral: Correlation Alignment for Deep Domain Adaptation. European Conference on Computer Vision, Springer.10.1007/978-3-319-49409-8_35 ↗
9. Imagenet classification with deep convolutional neural networks
10. Wikipedia Contributors (2021, May 19). Norm (Mathematics)—Wikipedia, The Free Encyclopedia. Available online: https://en.wikipedia.ahut.cf/w/index.php?title=Norm_(mathematics)&oldid=1020979856.
11. Zhang, H., Goodfellow, I., Metaxas, D., and Odena, A. (2019, January 9–15). Self-attention generative adversarial networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA.
12. Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., and Shlens, J. (2019). Stand-alone self-attention in vision models. arXiv.
13. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention is all you need. arXiv.
14. Saenko, K., Kulis, B., Fritz, M., and Darrell, T. (2010). Adapting visual category models to new domains. European Conference on Computer Vision, Springer.10.1007/978-3-642-15561-1_16 ↗
15. Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., and Darrell, T. (2014). Deep domain confusion: Maximizing for domain invariance. arXiv.
16. Long, M., Cao, Z., Wang, J., and Jordan, M.I. (2018). Conditional adversarial domain adaptation. Advances in Neural Information Processing Systems, NeurIPS.
17. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Li, F.F. (2009, January 20–25). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami Beach, FL, USA.10.1109/CVPR.2009.5206848 ↗