Over the past decade, deep-learning-based representations have demonstrated remarkable
performance in academia and industry. The learning capability of convolutional neural …

The research advances concerning the typical architectures of convolutional neural
networks (CNNs) as well as their optimizations are analyzed and elaborated in detail in this …

Recent advances in single image super-resolution (SISR) have achieved extraordinary
performance, but the computational cost is too heavy to apply in edge devices. To alleviate …

Dynamic neural network is an emerging research topic in deep learning. Compared to static
models which have fixed computational graphs and parameters at the inference stage …

The growing energy and performance costs of deep learning have driven the community to
reduce the size of neural networks by selectively pruning components. Similarly to their …

This paper describes a simple technique to analyze Generative Adversarial Networks
(GANs) and create interpretable controls for image synthesis, such as change of viewpoint …

Neural network pruning offers a promising prospect to facilitate deploying deep neural
networks on resource-limited devices. However, existing methods are still challenged by the …

Recently proposed knowledge distillation approaches based on feature-map transfer
validate that intermediate layers of a teacher model can serve as effective targets for training …

Domain-specific hardware is becoming a promising topic in the backdrop of improvement
slow down for general-purpose processors due to the foreseeable end of Moore's Law …

Pre-trained language models such as BERT have proven to be highly effective for natural
language processing (NLP) tasks. However, the high demand for computing resources in …