paper-with-me

홈 › Papers

RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs

2021-02-09 · Zhiwei Xu, Thalaiyasingam Ajanthan, Vibhav Vineet, Richard Hartley

Although 3D Convolutional Neural Networks are essential for most learning based applications involving dense 3D data, their applicability is limited due to excessive memory and computational requirements. Compressing such networks by pruning therefore becomes highly desirable. However, pruning 3D CNNs is largely unexplored possibly because of the complex nature of typical pruning algorithms that embeds pruning into an iterative optimization paradigm. In this work, we introduce a Resource Aware Neuron Pruning (RANP) algorithm that prunes 3D CNNs at initialization to high sparsity levels. Specifically, the core idea is to obtain an importance score for each neuron based on their sensitivity to the loss function. This neuron importance is then reweighted according to the neuron resource consumption related to FLOPs or memory. We demonstrate the effectiveness of our pruning method on 3D semantic segmentation with widely used 3D-UNets on ShapeNet and BraTS'18 datasets, video classification with MobileNetV2 and I3D on UCF101 dataset, and two-view stereo matching with Pyramid Stereo Matching (PSM) network on SceneFlow dataset. In these experiments, our RANP leads to roughly 50%-95% reduction in FLOPs and 35%-80% reduction in memory with negligible loss in accuracy compared to the unpruned networks. This significantly reduces the computational resources required to train 3D CNNs. The pruned network obtained by our algorithm can also be easily scaled up and transferred to another dataset for training.

📄 PDF Abstract BibTeX arXiv:2103.08457

Code (1)

zwxu064/RANP 공식 구현 pytorch

Tasks

3D Semantic SegmentationSemantic SegmentationStereo MatchingVideo Classification

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…
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…
Batch Normalization 설명 없음
Average Pooling 설명 없음
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Similar Papers 제목 키워드 기반

RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs

2020-10-06 · Zhiwei Xu, Thalaiyasingam Ajanthan, Vibhav Vineet, Richard Hartley

Although 3D Convolutional Neural Networks (CNNs) are essential for most learning based applications involving dense 3D data, their applicability is limited due to excessive memory and computational requirements. Compress…

3D Semantic SegmentationSemantic SegmentationVideo Classification

OSSuM: A Gradient-Free Approach For Pruning Neural Networks At Initialization

2021-09-29 · Vinu Sankar Sadasivan, Jayesh Malaviya, Anirban Dasgupta

Pruning overparameterized neural networks to obtain memory-and-compute-efficient sparse networks is an active area of research. Recent works attempt to prune neural networks at initialization to design sparse networks th…

Structured vs. Unstructured Pruning: An Exponential Gap

2026-02-13 · Davide Ferre', Frédéric Giroire, Frederik Mallmann-Trenn, Emanuele Natale arxiv

The Strong Lottery Ticket Hypothesis (SLTH) states that large, randomly initialized neural networks contain sparse subnetworks capable of approximating a target function at initialization without training, suggesting tha…

Recent Advances on Neural Network Pruning at Initialization

2021-03-11 · Huan Wang, Can Qin, Yue Bai, Yulun Zhang 외

Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network. This pap…

BenchmarkingNetwork Pruning

N2NSkip: Learning Highly Sparse Networks using Neuron-to-Neuron Skip Connections

2022-08-07 · Arvind Subramaniam, Avinash Sharma

The over-parametrized nature of Deep Neural Networks leads to considerable hindrances during deployment on low-end devices with time and space constraints. Network pruning strategies that sparsify DNNs using iterative pr…

Network Pruning