Computation-Performance Optimization of Convolutional Neural Networks with Redundant Kernel Removal
Deep Convolutional Neural Networks (CNNs) are widely employed in modern computer vision algorithms, where the input image is convolved iteratively by many kernels to extract the knowledge behind it. However, with the depth of convolutional layers getting deeper and deeper in recent years, the enormous computational complexity makes it difficult to be deployed on embedded systems with limited hardware resources. In this paper, we propose two computation-performance optimization methods to reduce the redundant convolution kernels of a CNN with performance and architecture constraints, and apply it to a network for super resolution (SR). Using PSNR drop compared to the original network as the performance criterion, our method can get the optimal PSNR under a certain computation budget constraint. On the other hand, our method is also capable of minimizing the computation required under a given PSNR drop.
Code (2)
Tasks
Super-ResolutionSimilar Papers 제목 키워드 기반
Content-Aware Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. Specifically, the standard convolution traverses the input images/features using a slid…
Efficient Hardware Realization of Convolutional Neural Networks using Intra-Kernel Regular Pruning
The recent trend toward increasingly deep convolutional neural networks (CNNs) leads to a higher demand of computational power and memory storage. Consequently, the deployment of CNNs in hardware has become more challeng…
Multi-hop Convolutions on Weighted Graphs
Graph Convolutional Networks (GCNs) have made significant advances in semi-supervised learning, especially for classification tasks. However, existing GCN based methods have two main drawbacks. First, to increase the rec…
Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs
Deep neural networks have achieved remarkable accuracy in many artificial intelligence applications, e.g. computer vision, at the cost of a large number of parameters and high computational complexity. Weight pruning can…
DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks
Convolution operator is the core of convolutional neural networks (CNNs) and occupies the most computation cost. To make CNNs more efficient, many methods have been proposed to either design lightweight networks or compr…