Dynamic Pruning of CNN networks

Fragoulis, Nikolaos; Theodorakopoulos, Ilias; Pothos, Vasileios K.; Vassalos, Evangelos

doi:10.1109/iisa.2019.8900711

Cited by 5 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method outperforms the state-of-the-art pruning methods in terms of parameters and FLOPs when it is tested on CIFAR dataset for VGG-16, ResNet-20 and DenseNet-40 models. A dynamic channel pruning method is presented in [20], which adds channel-wise sparsity at the output of each convolutional layer by introducing Learning Kernel-Activation switch module (LKAM). This module activates and de-activates each kernel dynamically depending upon the input content.…”

Section: A Network Compression Using Pruning Methodsmentioning

confidence: 99%

“…This whole process is carried out before applying any compression method. With the proposed network compression scheme, we first compress network using Soft Filter Pruning (SFP) and evaluate system for different values of pruning ratios (P%) including 10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95. The model's accuracy and error have been determined across each pruning ratio and their learning curves are shown in Figure 8.…”

Section: Evaluation Of Soft Filter Pruning (Sfp) Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Resource-Restricted Environments Based Memory-Efficient Compressed Convolutional Neural Network Model for Image-Level Object Classification

et al. 2023

View full text Add to dashboard Cite

In the past decade, Convolutional Neural Networks (CNNs) have achieved tremendous success in solving complex classification problems. CNN architectures require an excessive number of computations to achieve high accuracy. However, these models are deficient due to the heavy cost of storage and energy, which prohibits the application of CNNs to resource-constrained edge-devices. Hence, developing aggressive optimization schemes for efficient deployment of CNNs on edge devices has become the most important requirement. To find the optimal approach, we present a resource-limited environment based memoryefficient network compression model for image-level object classification. The main aim is to compress CNN architecture by achieving low computational cost and memory requirements without dropping system's accuracy. To achieve the said goal, we propose a network compression strategy, that works in a collaborative manner, where Soft Filter Pruning is first applied to reduce the computational cost of the model. In the next step, the model is divided into No-Pruning Layers (NP-Layers) and Pruning Layers (P-Layers). Incremental Quantization is applied to P-Layers due to irregular weights distribution, while for NP-Layers, we propose a novel Optimized Quantization algorithm for the quantization of weights up to optimal levels obtained from the Optimizer. This scheme is designed to achieve the best trade-off between compression ratio and accuracy of the model. Our proposed system is validated for image-level object classification on LeNet-5, CIFARquick, and VGG-16 networks using MNIST, CIFAR-10, and ImageNet ILSVRC2012 datasets respectively. We have achieved high compression ratio with negligible accuracy drop, outperforming the state-of-the-art methods.

show abstract

Section: A Network Compression Using Pruning Methodsmentioning

confidence: 99%