Abstract
By utilizing unsupervised domain adaptation (UDA), knowledge can be transferred from a label-rich source domain to a target domain that contains relevant information but lacks labels. Many existing UDA algorithms suffer from directly using raw images as input, resulting in models that overly focus on redundant information and exhibit poor generalization capability. To address this issue, we attempt to improve the performance of unsupervised domain adaptation by employing the Fourier method (FTF). Specifically, FTF is inspired by the observation that the amplitude of the Fourier spectrum primarily captures low-level statistical information. In FTF, we effectively incorporate low-level information from the target domain into the source domain by fusing the amplitudes of both domains in the Fourier domain. Additionally, we observe that extracting features from batches of images can eliminate redundant information while retaining class-specific features relevant to the task. Building upon this observation, we apply the Fourier transform at the data stream level for the first time. To further align multiple sources of data, we introduce the concept of correlation alignment. We evaluate the effectiveness of our FTF method, we conducted evaluations on four benchmark datasets for domain adaptation, including Office-31, Office-Home, ImageCLEF-DA, and Office-Caltech. Our results demonstrate superior performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018). https://doi.org/10.1109/TPAMI.2017.2699184
Deng, Z., Luo, Y., Zhu, J.: Cluster alignment with a teacher for unsupervised domain adaptation. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9943–9952 (2019). https://doi.org/10.1109/ICCV.2019.01004
Frigo, M., Johnson, S.: Fftw: an adaptive software architecture for the fft. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP’98 (Cat. No.98CH36181). vol. 3, pp. 1381–1384 (1998). https://doi.org/10.1109/ICASSP.1998.681704
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(59), 1–35 (2016). http://jmlr.org/papers/v17/15-239.html
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2066–2073 (2012). https://doi.org/10.1109/CVPR.2012.6247911
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2016)
Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 1989–1998. PMLR (10–15 Jul 2018). https://proceedings.mlr.press/v80/hoffman18a.html
Huang, J., Guan, D., Xiao, A., Lu, S.: Rda: robust domain adaptation via fourier adversarial attacking. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 8968–8979 (2021). https://api.semanticscholar.org/CorpusID:235359088
ImageCLEF: Imageclef-the clef cross language image retrieval track (2014). https://www.imageclef.org/. Accessed 25 June 2023
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998). https://doi.org/10.1109/5.726791
Li, Y., Yang, C., Chen, Y., Zhang, Y.: Unsupervised domain adaptation with structural attribute learning networks. Neurocomputing 415, 96–105 (2020). https://doi.org/10.1016/j.neucom.2020.07.054, https://www.sciencedirect.com/science/article/pii/S0925231220311620
Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: Neural Information Processing Systems (2017). https://api.semanticscholar.org/CorpusID:46784066
Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer feature learning with joint distribution adaptation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (Dec 2013)
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 2208–2217. PMLR (06–11 Aug 2017). https://proceedings.mlr.press/v70/long17a.html
Luo, Y.W., Ren, C.X., Dai, D.Q., Yan, H.: Unsupervised domain adaptation via discriminative manifold propagation. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1653–1669 (2022). https://doi.org/10.1109/TPAMI.2020.3014218
Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22(2), 199–210 (2011). https://doi.org/10.1109/TNN.2010.2091281
Portalés, C., Gimeno, J., Salvador, A., GarcÃa-Fadrique, A., Casas-Yrurzum, S.: Mixed reality annotation of robotic-assisted surgery videos with real- time tracking and stereo matching. Comput. Graph. 110, 125–140 (2023). https://doi.org/10.1016/j.cag.2022.12.006, https://www.sciencedirect.com/science/article/pii/S0097849322002291
Rangwani, H., Aithal, S.K., Mishra, M., Jain, A., Radhakrishnan, V.B.: A closer look at smoothness in domain adversarial training. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 162, pp. 18378–18399. PMLR (17–23 Jul 2022). https://proceedings.mlr.press/v162/rangwani22a.html
Ruan, H., et al.: Gnet: 3d object detection from point cloud with geometry-aware network. In: 2022 IEEE International Conference on Cyborg and Bionic Systems (CBS), pp. 190–195 (2023). https://doi.org/10.1109/CBS55922.2023.10115327
Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) Computer Vision - ECCV 2010, pp. 213–226. Springer, Berlin Heidelberg, Berlin, Heidelberg (2010)
Sakouhi, T., Akaichi, J.: Dynamic and multi-source semantic annotation of raw mobility data using geographic and social media data. Pervasive Mob. Comput. 71, 101310 (2021). https://api.semanticscholar.org/CorpusID:232328241
Sun, B., Saenko, K.: Deep coral: correlation alignment for deep domain adaptation. In: ECCV Workshops (2016). https://api.semanticscholar.org/CorpusID:12453047
Tong, J., Chen, T., Wang, Q., Yao, Y.: Few-shot object detection via understanding convolution and attention. In: Yu, S., Zhang, Z., Yuen, P.C., Han, J., Tan, T., Guo, Y., Lai, J., Zhang, J. (eds.) Pattern Recognition and Computer Vision, pp. 674–687. Springer International Publishing, Cham (2022)
Wang, J., Feng, W., Chen, Y., Yu, H., Huang, M., Yu, P.S.: Visual domain adaptation with manifold embedded distribution alignment. In: Proceedings of the 26th ACM International Conference on Multimedia (2018). https://api.semanticscholar.org/CorpusID:49883347
Wang, M., et al.: Boosting unsupervised domain adaptation: a fourier approach. Knowl.-Based Syst. 264, 110325 (2023). https://doi.org/10.1016/j.knosys.2023.110325, https://www.sciencedirect.com/science/article/pii/S0950705123000758
Wu, X., Yuan, X., Cui, Y., Zhao, C.: Rgb-d road segmentation based on geometric prior information. In: Liu, Q., Wang, H., Ma, Z., Zheng, W., Zha, H., Chen, X., Wang, L., Ji, R. (eds.) Pattern Recognition and Computer Vision, pp. 434–445. Springer Nature Singapore, Singapore (2024)
Xiao, N., Zhang, L.: Dynamic weighted learning for unsupervised domain adaptation. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15237–15246 (2021). https://api.semanticscholar.org/CorpusID:232352345
Xie, Q., Luong, M.T., Hovy, E., Le, Q.V.: Self-training with noisy student improves imagenet classification. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684–10695 (2020). https://doi.org/10.1109/CVPR42600.2020.01070
Xu, B., Liu, Q., Huang, T.: A discrete-time projection neural network for sparse signal reconstruction with application to face recognition. IEEE Trans. Neural Netw. Learn. Syst. 30(1), 151–162 (2018)
Yang, C., Guo, X., Chen, Z., Yuan, Y.: Source free domain adaptation for medical image segmentation with fourier style mining. Med. Image Anal. 79, 102457 (2022). https://doi.org/10.1016/j.media.2022.102457, https://www.sciencedirect.com/science/article/pii/S1361841522001049
Yang, S., Lian, C., Zeng, Z., Xu, B., Zang, J., Zhang, Z.: A multi-view multi-scale neural network for multi-label ecg classification. IEEE Trans. Emerg. Top. Comput. Intell. 7(3), 648–660 (2023). https://doi.org/10.1109/TETCI.2023.3235374
Yang, Y., Soatto, S.: Fda: fourier domain adaptation for semantic segmentation. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4084–4094 (2020). https://doi.org/10.1109/CVPR42600.2020.00414
Yao, S., Kang, Q., Zhou, M., Rawa, M.J., Albeshri, A.: Discriminative manifold distribution alignment for domain adaptation. IEEE Trans. Syst. Man Cybern. Syst. 53(2), 1183–1197 (2023). https://doi.org/10.1109/TSMC.2022.3195239
Zhang, Y., Xie, S., Davison, B.D.: Transductive learning via improved geodesic sampling. In: British Machine Vision Conference (2019). https://api.semanticscholar.org/CorpusID:198234065
Zhu, Y., et al.: Multi-representation adaptation network for cross-domain image classification. Neural Netw. Off. J. Int. Neural Netw. Soc. 119, 214–221 (2019). https://api.semanticscholar.org/CorpusID:201700545
Acknowledgements
This work was supported by the National Key R&D Program of China under Grant 2023YFB3406800, the National Natural Science Foundation of China under Grant 62206204, and the Natural Science Foundation of Chongqing, China (CSTB2023NSCQ-MSX0932).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Luo, L., Xu, B., Zhang, Q., Lian, C., Luo, J. (2025). A Fourier Transform Framework for Domain Adaptation. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2024. Lecture Notes in Computer Science, vol 15038. Springer, Singapore. https://doi.org/10.1007/978-981-97-8685-5_2
Download citation
DOI: https://doi.org/10.1007/978-981-97-8685-5_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-8684-8
Online ISBN: 978-981-97-8685-5
eBook Packages: Computer ScienceComputer Science (R0)