Research On Adaptation and Generalization Issues in Image Processing
DOI:
https://doi.org/10.54097/x85q2942Keywords:
Image processing; Adaptation; Generalization; Deep learning.Abstract
Image processing has been a fundamental research problem in the computer vision community, which aims to construct models to recognize the content in a given image. With the accuracy and speed of image recognition have been making breakthroughs in recent years, yet the problems of model adaptation and generalization are still challenging topics. Adaptation problems involve the effective transfer of knowledge learned in one domain to another domain, despite distribution differences between them, to enhance the model's performance in the target domain. On the other hand, generalization problems refer to how well the model adapts the knowledge acquired from the training dataset to previously unseen, new data samples, i.e., its performance on the test dataset. This review focuses on mainstream methods and their effectiveness in addressing adaptation and generalization issues in the current image processing domain. It analyzes the existing challenges and proposes potential solutions, further exploring how to improve the model's expressive power while maintaining its generalization performance.
Downloads
References
Kouw, W. M., & Loog, M. (2019). A review of domain adaptation without target labels. IEEE transactions on pattern analysis and machine intelligence, 43(3), 766-785.
Wang, M., & Deng, W. (2018). Deep visual domain adaptation: A survey. Neurocomputing, 312, 135-153.
Zhuo, J., Wang, S., & Huang, Q. (2022). Uncertainty modeling for robust domain adaptation under noisy environments. IEEE Transactions on Multimedia.
Zhang, L., & Gao, X. (2022). Transfer adaptation learning: A decade survey. IEEE Transactions on Neural Networks and Learning Systems.
Shao, L., Zhu, F., & Li, X. (2014). Transfer learning for visual categorization: A survey. IEEE transactions on neural networks and learning systems, 26(5), 1019-1034.
Zhou, K., Liu, Z., Qiao, Y., Xiang, T., & Loy, C. C. (2022). Domain generalization: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence.
Li, D., Yang, Y., Song, Y. Z., & Hospedales, T. M. (2017). Deeper, broader and artier domain generalization. In Proceedings of the IEEE international conference on computer vision (pp. 5542-5550).
Li, H., Pan, S. J., Wang, S., & Kot, A. C. (2018). Domain generalization with adversarial feature learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5400-5409).
Hospedales, T., Antoniou, A., Micaelli, P., & Storkey, A. (2021). Meta-learning in neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(9), 5149-5169.
Yuan, Y., Zheng, G., Wong, K. K., Ottersten, B., & Luo, Z. Q. (2020). Transfer learning and meta learning-based fast downlink beamforming adaptation. IEEE Transactions on Wireless Communications, 20(3), 1742-1755.
Hoyer, L., Dai, D., Wang, H., & Van Gool, L. (2023). MIC: Masked image consistency for context-enhanced domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 11721-11732).
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
