相关论文: Data Agnostic Filter Gating for Efficient Deep Net…

Despite the promising results of convolutional neural networks (CNNs), their application on devices with limited resources is still a big challenge; this is mainly due to the huge memory and computation requirements of the CNN. To counter…

Despite the remarkable performance, modern deep neural networks are inevitably accompanied by a significant amount of computational cost for learning and deployment, which may be incompatible with their usage on edge devices. Recent efforts…

Filter pruning is effective to reduce the computational costs of neural networks. Existing methods show that updating the previous pruned filter would enable large model capacity and achieve better performance. However, during the iterative…

Deep neural networks (DNNs) have demonstrated remarkable success in various fields. However, the large number of floating-point operations (FLOPs) in DNNs poses challenges for their deployment in resource-constrained applications, e.g.,…

We propose an efficient and unified framework, namely ThiNet, to simultaneously accelerate and compress CNN models in both training and inference stages. We focus on the filter level pruning, i.e., the whole filter would be discarded if it…

Neural network pruning has remarkable performance for reducing the complexity of deep network models. Recent network pruning methods usually focused on removing unimportant or redundant filters in the network. In this paper, by exploring…

Previous works utilized ''smaller-norm-less-important'' criterion to prune filters with smaller norm values in a convolutional neural network. In this paper, we analyze this norm-based criterion and point out that its effectiveness depends…

Recent advances in pruning of neural networks have made it possible to remove a large number of filters or weights without any perceptible drop in accuracy. The number of parameters and that of FLOPs are usually the reported metrics to…

Convolutional Neural Network (CNN) is more and more widely used in various fileds, and its computation and memory-demand are also increasing significantly. In order to make it applicable to limited conditions such as embedded application,…

Neural networks performance has been significantly improved in the last few years, at the cost of an increasing number of floating point operations per second (FLOPs). However, more FLOPs can be an issue when computational resources are…

Neural network pruning offers a promising prospect to facilitate deploying deep neural networks on resource-limited devices. However, existing methods are still challenged by the training inefficiency and labor cost in pruning designs, due…

Convolutional Neural Network (CNN) has an amount of parameter redundancy, filter pruning aims to remove the redundant filters and provides the possibility for the application of CNN on terminal devices. However, previous works pay more…

Filter pruning has gained widespread adoption for the purpose of compressing and speeding up convolutional neural networks (CNNs). However, existing approaches are still far from practical applications due to biased filter selection and…

This paper proposes a new learning paradigm called filter grafting, which aims to improve the representation capability of Deep Neural Networks (DNNs). The motivation is that DNNs have unimportant (invalid) filters (e.g., l1 norm close to…

Filter pruning is one of the most effective ways to accelerate and compress convolutional neural networks (CNNs). In this work, we propose a global filter pruning algorithm called Gate Decorator, which transforms a vanilla CNN module by…

Deeper and wider Convolutional Neural Networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such over-parameterized neural network has received increased attention. A typical pruning algorithm is a…

Deep neural networks (DNNs) are usually over-parameterized to increase the likelihood of getting adequate initial weights by random initialization. Consequently, trained DNNs have many redundancies which can be pruned from the model to…

This paper introduces channel gating, a dynamic, fine-grained, and hardware-efficient pruning scheme to reduce the computation cost for convolutional neural networks (CNNs). Channel gating identifies regions in the features that contribute…

Channel pruning has received ever-increasing focus on network compression. In particular, class-discrimination based channel pruning has made major headway, as it fits seamlessly with the classification objective of CNNs and provides good…

Modern pattern recognition methods are based on convolutional networks since they are able to learn complex patterns that benefit the classification. However, convolutional networks are computationally expensive and require a considerable…