[M][B] Fourier-basis noise data augmentation

BACHELOR Assignment

Fourier-basis noise data augmentation.

Type: Bachelor CS 

Period: TBD

Student: (Unassigned)

If you are interested please contact :

Description:

Traditional image augmentations include but are not limited to rotation, crop, and flip, which mainly operate in the spatial domain. By using image data augmentation, the variety of the data increases, improving model robustness. Instead of operating in the spatial domain, this research aims at exploring whether augmenting the frequency information of images helps improve the robustness of models under adversarial attacks [2]. To augment frequency information, Fourier basis noise is used [1], which is additive noise in a specific frequency.  The frequency-augmented images are further used for training computer vision models, for which the robustness towards adversarial attack is evaluated and compared with state-of-the-art approaches.

References:

[1] Yin, D., Lopes, R. G., Shlens, J., Cubuk, E. D., & Gilmer, J. (2019). A Fourier Perspective on Model Robustness in Computer Vision. doi:10.48550/ARXIV.1906.08988

[2] S. Y. Khamaiseh, D. Bagagem, A. Al-Alaj, M. Mancino and H. W. Alomari, "Adversarial Deep Learning: A Survey on Adversarial Attacks and Defense Mechanisms on Image Classification," in IEEE Access, vol. 10, pp. 102266-102291, 2022, doi: 10.1109/ACCESS.2022.3208131

Cookies on utwente.nl

We use cookies and similar technologies and process your personal data (e.g., IP address) to personalise content and ads, to integrate media from third-party providers, or to analyse traffic. Data processing may also occur as a result of cookies being set. The data processing may take place with your consent. You have the right to withhold consent and to change or revoke your consent at a later time. For more information on the use of your data, please visit our privacy statement or cookie policy.