paper-with-me

홈 › Papers

Neural Network Compression by Joint Sparsity Promotion and Redundancy Reduction

2022-10-14 · Tariq M. Khan, Syed S. Naqvi, Antonio Robles-Kelly, Erik Meijering

Compression of convolutional neural network models has recently been dominated by pruning approaches. A class of previous works focuses solely on pruning the unimportant filters to achieve network compression. Another important direction is the design of sparsity-inducing constraints which has also been explored in isolation. This paper presents a novel training scheme based on composite constraints that prune redundant filters and minimize their effect on overall network learning via sparsity promotion. Also, as opposed to prior works that employ pseudo-norm-based sparsity-inducing constraints, we propose a sparse scheme based on gradient counting in our framework. Our tests on several pixel-wise segmentation benchmarks show that the number of neurons and the memory footprint of networks in the test phase are significantly reduced without affecting performance. MobileNetV3 and UNet, two well-known architectures, are used to test the proposed scheme. Our network compression method not only results in reduced parameters but also achieves improved performance compared to MobileNetv3, which is an already optimized architecture.

📄 PDF Abstract BibTeX arXiv:2210.07451

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Network Compression

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
Test 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …
ReLU6 ReLU6 is a modification of the rectified linear unit where we limit the activation to a maximum size of $6$. This is due to increased…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression

2019-02-03 · Jie Zhang, Xiaolong Wang, Dawei Li, Shalini Ghosh 외

State-of-the-art deep model compression methods exploit the low-rank approximation and sparsity pruning to remove redundant parameters from a learned hidden layer. However, they process each hidden layer individually whi…

Knowledge DistillationModel Compression

Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression

2018-12-11 · CVPR 2019 6 · Yuchao Li, Shaohui Lin, Baochang Zhang, Jianzhuang Liu 외

Compressing convolutional neural networks (CNNs) has received ever-increasing research focus. However, most existing CNN compression methods do not interpret their inherent structures to distinguish the implicit redundan…

ClusteringModel Compression

Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training

2022-11-19 · Zhenglun Kong, Haoyu Ma, Geng Yuan, Mengshu Sun 외

Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression …

ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers

2018-12-31 · Ao Ren, Tianyun Zhang, Shaokai Ye, Jiayu Li 외

To facilitate efficient embedded and hardware implementations of deep neural networks (DNNs), two important categories of DNN model compression techniques: weight pruning and weight quantization are investigated. The for…

Model CompressionQuantization

Empirical Minimal-Realisation Compression of Deep Neural Networks via Controllability-Observability Tests

2026-07-05 · Anis Hamadouche, Amir Hussain arxiv

Deep neural networks often contain substantial hidden-state redundancy, but most compression methods operate directly on weights, neurons, or quantised representations without explicitly characterising the dynamical role…