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 …

The remarkable performance of deep Convolutional neural networks (CNNs) is generally
attributed to their deeper and wider architectures, which can come with significant …

Abstract Recently, Vision Transformer (ViT) has continuously established new milestones in
the computer vision field, while the high computation and memory cost makes its …

This paper proposes an efficient neural network (NN) architecture design methodology
called Chameleon that honors given resource constraints. Instead of developing new …

This paper aims to quantitatively explain the rationales of each prediction that is made by a
pre-trained convolutional neural network (CNN). We propose to learn a decision tree, which …

Recently, a new trend of exploring sparsity for accelerating neural network training has
emerged, embracing the paradigm of training on the edge. This paper proposes a novel …

Channel pruning has been broadly recognized as an effective technique to reduce the
computation and memory cost of deep convolutional neural networks. However …

Structured weight pruning is a representative model compression technique of DNNs to
reduce the storage and computation requirements and accelerate inference. An automatic …

It is well known that deep neural networks (DNNs) are vulnerable to adversarial attacks,
which are implemented by adding crafted perturbations onto benign examples. Min-max …

This article focuses on filter-level network pruning. A novel pruning method, termed CLR-
RNF, is proposed. We first reveal a “long-tail” pruning problem in magnitude-based weight …