5 papers
CASISR: Circular Arbitrary-Scale Image Super-Resolution
Honggui Li, Zhengyang Zhang, Dingtai Li +11
The generalization performance (GP) of deep learning-based arbitrary-scale image super-resolution (ASISR) methods is subject to limited training datasets and unlimited testing data…
FAROS: Robust Federated Learning with Adaptive Scaling against Backdoor Attacks
Chenyu Hu, Qiming Hu, Sinan Chen +3
Federated Learning (FL) enables multiple clients to collaboratively train a shared model without exposing local data. However, backdoor attacks pose a significant threat to FL. The…
Automatic Syntax Error Repair for Discrete Controller Synthesis using Large Language Model
Yusei Ishimizu, Takuto Yamauchi, Sinan Chen +3
Discrete Controller Synthesis (DCS) is a powerful formal method for automatically generating specifications of discrete event systems. However, its practical adoption is often hind…
CECGSR: Circular ECG Super-Resolution
Honggui Li, Zhengyang Zhang, Dingtai Li +11
Background and Objective: The electrocardiogram (ECG) plays a crucial role in the diagnosis and treatment of various cardiac diseases. ECG signals suffer from low-resolution (LR) d…
CIC: Circular Image Compression
Honggui Li, Sinan Chen, Dingtai Li +9
Learned image compression (LIC) is currently the cutting-edge method. However, the inherent difference between testing and training images of LIC results in performance degradation…