Deep neural networks (DNNs) require a large amount of manually labeled training data to
make significant achievements. However, manual labeling is laborious and costly. In this …

The mechanical equipment often faces complex working environments in practical operating
conditions, and the external environmental interference generated by operating conditions …

The easy scalability and low cost of range-free localization algorithms have led to their wide
attention and application in node localization of wireless sensor networks. However, the …

The inspection of cracks on the surface of tunnel linings is a common method of evaluate the
condition of the tunnel. In particular, determining the thickness and shape of a crack is …

Image recognition research based on the Generative Adversarial Networks (GAN) has been
widely used in various specialized technical fields because of its universality, adaptability …

A deep-learning technology for knowledge transfer is necessary to advance and optimize
efficient knowledge distillation. Here, we aim to develop a new adversarial optimization …

In recent years, facial attribute editing has been successfully used to effectively change face
images of various attributes based on generative adversarial networks and encoder …