Abstract We proposed a Prior Gradient Mask Guided Pruning-aware Fine-Tuning (PGMPF)
framework to accelerate deep Convolutional Neural Networks (CNNs). In detail, the …

While deep neural networks have achieved superior performance in a variety of intelligent
applications, the increasing computational complexity makes them difficult to be deployed …

Filter pruning, a representative model compression technique, has been widely used to
compress and accelerate sophisticated deep neural networks on resource-constrained …

Network pruning and knowledge distillation, as two effective network compression
techniques, have drawn extensive attention due to their success in reducing model …

Filter pruning and low-rank decomposition are two of the foundational techniques for
structured compression. Although recent efforts have explored hybrid approaches aiming to …

Abstract Model compression techniques, such as network pruning, quantization and
knowledge distillation, are essential for deploying large Convolutional Neural Networks …

Filter pruning method introduces structural sparsity by removing selected filters and is thus
particularly effective for reducing complexity. Previous works empirically prune networks …

Conventional pruning techniques typically focus on evaluating a single structure in the
network, such as the convolutional layer or batch normalization layer, to identify pruning …

The filter pruning method introduces structural sparsity by removing selected filters and is
thus particularly effective for reducing complexity. However, previous works face two …

Designing a deep neural network (DNN) for efficient operation in low-resource environments
necessitates strategic application of compression techniques. Filter pruning and low-rank …