In recent years, deep neural networks (DNNs) have received increased attention, have been
applied to different applications, and achieved dramatic accuracy improvements in many …

Object detection, one of the most fundamental and challenging problems in computer vision,
seeks to locate object instances from a large number of predefined categories in natural …

Object detection is a fundamental but challenging issue in the field of generic image
analysis; it plays an important role in a wide range of applications and has been receiving …

In this paper, we introduce a new channel pruning method to accelerate very deep
convolutional neural networks. Given a trained CNN model, we propose an iterative two …

Network pruning is widely used for reducing the heavy inference cost of deep models in low-
resource settings. A typical pruning algorithm is a three-stage pipeline, ie, training (a large …

High demand for computation resources severely hinders deployment of large-scale Deep
Neural Networks (DNN) in resource constrained devices. In this work, we propose a …

We propose a new formulation for pruning convolutional kernels in neural networks to
enable efficient inference. We interleave greedy criteria-based pruning with fine-tuning by …

Model pruning seeks to induce sparsity in a deep neural network's various connection
matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent …

Deep neural networks (DNNs) have recently achieved great success in many visual
recognition tasks. However, existing deep neural network models are computationally …

We propose a novel deep network architecture for lifelong learning which we refer to as
Dynamically Expandable Network (DEN), that can dynamically decide its network capacity …