Pruning and quantization are core techniques used to reduce the inference costs of deep
neural networks. Among the state-of-the-art pruning techniques, magnitude-based pruning …

Many computer vision problems require image upsampling, where the number of pixels per
unit area is increased by inferring values in high-dimensional image space from …

The unprecedented success of deep neural networks (DNNs), especially convolutional
neural networks (CNNs), stems from its high representational power and capability to model …

Quantization and pruning are widely used to reduce the inference costs of deep neural
networks. In this work, we propose a framework to train deep neural networks using novel …