Intra-& extra-source exemplar-based style synthesis for improved domain generalization

Y Li, D Zhang, M Keuper, A Khoreva - International Journal of Computer …, 2024 - Springer
The generalization with respect to domain shifts, as they frequently appear in applications
such as autonomous driving, is one of the remaining big challenges for deep learning …

Intra-source style augmentation for improved domain generalization

Y Li, D Zhang, M Keuper… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
The generalization with respect to domain shifts, as they frequently appear in applications
such as autonomous driving, is one of the remaining big challenges for deep learning …

Artificial intelligence-based cardiovascular/stroke risk stratification in women affected by autoimmune disorders: a narrative survey

E Tiwari, D Shrimankar, M Maindarkar… - Rheumatology …, 2025 - Springer
Women are disproportionately affected by chronic autoimmune diseases (AD) like systemic
lupus erythematosus (SLE), scleroderma, rheumatoid arthritis (RA), and Sjögren's …

[HTML][HTML] Coarse-to-fine structure and semantic learning for single-sample SAR image generation

X Wang, B Hui, P Guo, R Jin, L Ding - Remote Sensing, 2024 - mdpi.com
Synthetic Aperture Radar (SAR) enables the acquisition of high-resolution imagery even
under severe meteorological and illumination conditions. Its utility is evident across a …

A two-stage model extraction attack on GANs with a small collected dataset

H Sun, T Zhu, W Chang, W Zhou - Computers & Security, 2024 - Elsevier
Due to their capacity for image generation, GAN models may be considered as a solution for
the use of private data, which enhances their commercial value. However, unlike …

Differentiable Image Data Augmentation and Its Applications: A Survey

J Shi, H Ghazzai, Y Massoud - IEEE Transactions on Pattern …, 2023 - ieeexplore.ieee.org
Data augmentation is an effective method to improve model robustness and generalization.
Conventional data augmentation pipelines are commonly used as preprocessing modules …

GAN Latent Space Manipulation Based Augmentation for Unbalanced Emotion Datasets

Y Xiong, J You, L Shen - 2023 International Joint Conference …, 2023 - ieeexplore.ieee.org
Learning with small or highly unbalanced datasets have long been an important area of
research in computer vision. Extracting features from these datasets is more difficult and the …

VSG-GAN: A high-fidelity image synthesis method with semantic manipulation in retinal fundus image

J Liu, S Xu, P He, S Wu, X Luo, Y Deng, H Huang - Biophysical Journal, 2024 - cell.com
In recent years, advancements in retinal image analysis, driven by machine learning and
deep learning techniques, have enhanced disease detection and diagnosis through …

[引用][C] XAI techniques for medical image patterns

MFF Fontes - 2024