-
Chapter and Conference Paper
ColorFormer: Image Colorization via Color Memory Assisted Hybrid-Attention Transformer
Automatic image colorization is a challenging task that attracts a lot of research interest. Previous methods employing deep neural networks have produced impressive results. However, these colorization images...
-
Article
Unsupervised domain adaptation with target reconstruction and label confusion in the common subspace
Deep neural networks can learn powerful and discriminative representations from a large number of labeled samples. However, it is typically costly to collect and annotate large-scale datasets, which limits the...
-
Article
Optimizing Extreme Learning Machine via Generalized Hebbian Learning and Intrinsic Plasticity Learning
Traditional extreme learning machine (ELM) has random weights between input layer and hidden layer, this kind of random feature map** brings non-discriminative feature space and unstable classification accur...
-
Article
A global simulation method for obtaining reduced reaction mechanisms for use in reactive blast wave flows
A finite rate chemistry solver usually consumes the largest part of the computing time in the numerical simulation of reactive flows. To reduce these costs, a global simulation method has been developed for sy...