This paper presents a new way to identify additional positive pairs for ...
The ubiquity of edge devices has led to a growing amount of unlabeled da...
Detecting actions in videos have been widely applied in on-device
applic...
In dermatological disease diagnosis, the private data collected by mobil...
Dermatological diseases pose a major threat to the global health, affect...
Supervised deep learning needs a large amount of labeled data to achieve...
Supervised deep learning needs a large amount of labeled data to achieve...
Many works have shown that deep learning-based medical image classificat...
Along with the progress of AI democratization, neural networks are being...
Contrastive learning (CL), a self-supervised learning approach, can
effe...
Deep learning models have been deployed in an increasing number of edge ...
Federated learning (FL) enables distributed clients to learn a shared mo...
The success of deep learning heavily depends on the availability of larg...
After a model is deployed on edge devices, it is desirable for these dev...
This work aims to enable on-device training of convolutional neural netw...