CorrNet: pearson correlation based pruning for efficient convolutional neural networks

Kumar, Aakash; Yin, Baocai; Shaikh, Ali Muhammad; Ali, Munawar; Wei, Wenyue

doi:10.1007/s13042-022-01624-5

Cited by 7 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accomplishing these objectives necessitates the computational costs reduction and memory requirements which aids in broadening the deep learning models applicability and being able to employ in a wide variety of applications namely embedded systems, real-time applications, and mobile devices. Although, several approaches available in the literature regarding coping with compressing CNNs have been introduced recently [32,33], pruning in this field emerges as a famous solution which is eliminating redundant weights out of initial networks. While techniques related to pruning were conceived in early era of the 1980s-1990s, and were able to be utilized in deep learning networks [32].…”

Section: Literature Workmentioning

confidence: 99%

“…In the meantime, these methodologies cease to anticipate filter redundancy during pruning. To remove the redundant feature maps in [33] proposed an approach based on the correlation between feature maps that are generated out of corresponding filter. This technique eliminates the redundant feature maps to aid in reducing the size of a model along with reduced computational cost plus being able to save many FLOPs too.…”

Section: Literature Workmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Bayesian CNN Model Compression using Bayes by Backprop and L1-Norm Regularization

Shaikh,

Zhao,

Kumar

et al. 2024

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

The swift advancement of convolutional neural networks (CNNs) in numerous real-world utilizations urges an elevation in computational cost along with the size of the model. In this context, many researchers steered their focus to eradicate these specific issues by compressing the original CNN models by pruning weights and filters, respectively. As filter pruning has an upper hand over the weight pruning method because filter pruning methods don’t impact sparse connectivity patterns. In this work, we suggested a Bayesian Convolutional Neural Network (BayesCNN) with Variational Inference, which prefaces probability distribution over weights. For the pruning task of Bayesian CNN, we utilized a combined version of L1-norm with capped L1-norm to help epitomize the amount of information that can be extracted through filter and control regularization. In this formation, we pruned unimportant filters directly without any test accuracy loss and achieved a slimmer model with comparative accuracy. The whole process of pruning is iterative and to validate the performance of our proposed work, we utilized several different CNN architectures on the standard classification dataset available. We have compared our results with non-Bayesian CNN models particularly, datasets such as CIFAR-10 on VGG-16, and pruned 75.8% parameters with float-point-operations (FLOPs) reduction of 51.3% without loss of accuracy and has achieved advancement in state-of-art.

show abstract

Section: Literature Workmentioning

confidence: 99%

Section: Literature Workmentioning

confidence: 99%

Efficient Bayesian CNN Model Compression using Bayes by Backprop and L1-Norm Regularization

Shaikh,

Zhao,

Kumar

et al. 2024

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, it is wise to calculate the statistic of each signal over time, namely the SLTVSFs, in order to better evaluate the non-stationary random signal. With the separated signal time-frequency spectrum, we can calculate the SLTVSFs via the weighted sliding statistics method [23]. Four SLTVSFs are used in this paper, the average, standard deviation, maximum, and bandwidth, which are defined as follows:…”

Section: Feature Similarity Decision Criterionmentioning

confidence: 99%

Environmental Interference Suppression by Hybrid Segmentation Algorithm for Open-Area Electromagnetic Capability Testing

Yang,

Chen,

Zhang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Compared with electromagnetic compatibility (EMC) testing in anechoic rooms, open-area EMC testing takes advantage of in situ and engine running status measurement but suffers from non-negligible external electromagnetic interference. This paper proposes a novel environmental interference suppression method (named the EMC environmental interference suppression algorithm (E2ISA)) that separates signals from backgrounds via image segmentation and recognizes the near–far site signal via a group of time-varying features based on the difference in the near-site EM radiative characteristic. We find that the proposed E2ISA method, which combines the deep learning segmentation network with the classical recognition methods, is able to suppress environmental interference signals accurately. The experiment results show that the accuracy of E2ISA reaches up to 95% in the face of VHF (Very High Frequency) EMC testing tasks.

show abstract

Federated Learning with Flexible Architectures

Park,

Joe-Wong

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

CorrNet: pearson correlation based pruning for efficient convolutional neural networks

Cited by 7 publications

References 28 publications

Efficient Bayesian CNN Model Compression using Bayes by Backprop and L1-Norm Regularization

Efficient Bayesian CNN Model Compression using Bayes by Backprop and L1-Norm Regularization

Environmental Interference Suppression by Hybrid Segmentation Algorithm for Open-Area Electromagnetic Capability Testing

Federated Learning with Flexible Architectures

Contact Info

Product

Resources

About