Despite the success of vision transformers (ViTs), they still suffer fro...
Semi-supervised learning (SSL) has achieved great success in leveraging ...
Deep networks have achieved great success in image rescaling (IR) task t...
Neural Architecture Search (NAS) aims to automatically find effective
ar...
Designing feasible and effective architectures under diverse computation...
Self-supervised learning (SSL) has achieved remarkable performance in
pr...
Deep neural networks have exhibited remarkable performance in image
supe...
Deep neural networks have achieved great success in many computer vision...
In real-world applications, data often come in a growing manner, where t...
Convolutional Neural Networks (CNNs) have achieved great success due to ...
One of the key steps in Neural Architecture Search (NAS) is to estimate ...
Designing feasible and effective architectures under diverse computation...
Designing effective architectures is one of the key factors behind the
s...
View synthesis aims to produce unseen views from a set of views captured...
We present Automatic Bit Sharing (ABS) to automatically search for optim...
Batch Normalization (BN) has been a standard component in designing deep...
Model compression aims to reduce the redundancy of deep networks to obta...
Generative adversarial networks (GANs) have shown remarkable success in
...
Neural architecture search (NAS) has gained increasing attention in the
...
Deep neural networks have exhibited promising performance in image
super...
Deep neural networks have exhibited promising performance in image
super...
Joint distribution matching (JDM) problem, which aims to learn bidirecti...
We study network pruning which aims to remove redundant channels/kernels...
Designing effective architectures is one of the key factors behind the
s...
Generating images via the generative adversarial network (GAN) has attra...
Channel pruning is one of the predominant approaches for deep model
comp...
Deep neural networks have exhibited promising performance in image
super...
Generative adversarial networks (GANs) aim to generate realistic data fr...
The depth is one of the key factors behind the great success of convolut...
Single-pixel cameras based on the concepts of compressed sensing (CS)
le...