paper-with-me

Papers

Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning

2016-11-16 · CVPR 2017 7 · Tien-Ju Yang, Yu-Hsin Chen, Vivienne Sze

Deep convolutional neural networks (CNNs) are indispensable to state-of-the-art computer vision algorithms. However, they are still rarely deployed on battery-powered mobile devices, such as smartphones and wearable gadgets, where vision algorithms can enable many revolutionary real-world applications. The key limiting factor is the high energy consumption of CNN processing due to its high computational complexity. While there are many previous efforts that try to reduce the CNN model size or amount of computation, we find that they do not necessarily result in lower energy consumption, and therefore do not serve as a good metric for energy cost estimation. To close the gap between CNN design and energy consumption optimization, we propose an energy-aware pruning algorithm for CNNs that directly uses energy consumption estimation of a CNN to guide the pruning process. The energy estimation methodology uses parameters extrapolated from actual hardware measurements that target realistic battery-powered system setups. The proposed layer-by-layer pruning algorithm also prunes more aggressively than previously proposed pruning methods by minimizing the error in output feature maps instead of filter weights. For each layer, the weights are first pruned and then locally fine-tuned with a closed-form least-square solution to quickly restore the accuracy. After all layers are pruned, the entire network is further globally fine-tuned using back-propagation. With the proposed pruning method, the energy consumption of AlexNet and GoogLeNet are reduced by 3.7x and 1.6x, respectively, with less than 1% top-5 accuracy loss. Finally, we show that pruning the AlexNet with a reduced number of target classes can greatly decrease the number of weights but the energy reduction is limited. Energy modeling tool and energy-aware pruned models available at http://eyeriss.mit.edu/energy.html

📄 PDF Abstract BibTeX arXiv:1611.05128

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
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…
Average Pooling 설명 없음
Local Response Normalization Local Response Normalization is a normalization layer that implements the idea of lateral inhibition. Lateral inhibition is a concept in neurobiology that refers to the…
Auxiliary Classifier Auxiliary Classifiers are type of architectural component that seek to improve the convergence of very deep networks. They are classifier heads we attach to layers before the…
Inception Module An Inception Module is an image model block that aims to approximate an optimal local sparse structure in a CNN. Put simply, it allows for us to use multiple types of filter…
Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…

Similar Papers 제목 키워드 기반

DANCE: Dynamic 3D CNN Pruning: Joint Frame, Channel, and Feature Adaptation for Energy Efficiency on the Edge

2026-03-18 · Mohamed Mejri, Ashiqur Rasul, Abhijit Chatterjee arxiv

Modern convolutional neural networks (CNNs) are workhorses for video and image processing, but fail to adapt to the computational complexity of input samples in a dynamic manner to minimize energy consumption. In this re…

Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent

2019-10-07 · ICLR 2020 1 · Dilin Wang, Meng Li, Lemeng Wu, Vikas Chandra 외

Designing energy-efficient networks is of critical importance for enabling state-of-the-art deep learning in mobile and edge settings where the computation and energy budgets are highly limited. Recently, Liu et al. (201…

GPU

Pruning of Convolutional Neural Networks Using Ising Energy Model

2021-02-10 · Hojjat Salehinejad, Shahrokh Valaee

Pruning is one of the major methods to compress deep neural networks. In this paper, we propose an Ising energy model within an optimization framework for pruning convolutional kernels and hidden units. This model is des…

A Theoretical Framework for Energy-Aware Gradient Pruning in Federated Learning

2026-03-23 · Emmanouil M. Athanasakos arxiv

Federated Learning (FL) is constrained by the communication and energy limitations of decentralized edge devices. While gradient sparsification via Top-K magnitude pruning effectively reduces the communication payload, i…

Federated Learning

Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization

2023-12-23 · Konstantinos Balaskas, Andreas Karatzas, Christos Sad, Kostas Siozios 외

Deep Neural Networks (DNNs) have shown significant advantages in a wide variety of domains. However, DNNs are becoming computationally intensive and energy hungry at an exponential pace, while at the same time, there is …

QuantizationReinforcement Learning (RL)