It is commonly believed that networks cannot be both accurate and robust, that gaining
robustness means losing accuracy. It is also generally believed that, unless making …

Neural networks have proven to be a highly effective tool for solving complex problems in
many areas of life. Recently, their importance and practical usability have further been …

Advances in deep learning, combined with availability of large datasets, have led to
impressive improvements in face presentation attack detection research. However, state of …

Multi-scale representation learning aims to leverage diverse features from different layers of
Convolutional Neural Networks (CNNs) for boosting the feature robustness to scale …

Accurate gland segmentation in histology tissue images is a critical but challenging task.
Although deep models have demonstrated superior performance in medical image …

Hybrid private inference (PI) protocol, which synergistically utilizes both multi-party
computation (MPC) and homomorphic encryption, is one of the most prominent techniques …

Deep neural networks have been the driving force behind the success in classification tasks,
eg, object and audio recognition. Impressive results and generalization have been achieved …

In this paper, we propose a Siamese graph learning (SGL) approach to alleviate aging
dataset bias. While numerous semi-supervised algorithms have been successfully applied …

Federated learning (FL) emerges to mitigate the privacy concerns in machine learning-
based services and applications, and personalized federated learning (PFL) evolves to …

This work investigates the functionality of Semantic information in Contrastive Learning
(SemCL). An advanced pretext task is designed: a contrast is performed between each …