paper-with-me

Papers

Automated Channel Pruning with Learned Importance

2021-09-29 · Łukasz Treszczotko, Pawel Kubik

Neural network pruning allows for significant reduction of model size and latency. However, most of the current network pruning methods do not consider channel interdependencies and a lot of manual adjustments are required before they can be applied to new network architectures. Moreover, these algorithms are often based on hand-picked, sometimes complicated heuristics and can require thousands of GPU computation hours. In this paper, we introduce a simple neural network pruning and fine-tuning framework that requires no manual heuristics, is highly efficient to train (2-6 times speed up compared to NAS-based competitors) and produces comparable performance. The framework contains 1) an automatic channel detection algorithm that groups the interdependent blocks of channels; 2) a non-iterative pruning algorithm that learns channel importance directly from feature maps while masking the coupled computational blocks using Gumbel-Softmax sampling and 3) a hierarchical knowledge distillation approach to fine-tune the pruned neural networks. We validate our pipeline on ImageNet classification, human segmentation and image denoising, creating lightweight and low latency models, easy to deploy on mobile devices. Using our pruning algorithm and hierarchical knowledge distillation for fine-tuning we are able to prune EfficientNet B0, EfficientNetV2 B0 and MobileNetV2 to 75% of their original FLOPs with no loss of accuracy on ImageNet. We release a set pruned backbones as Keras models - all of them proved beneficial when deployed in other projects.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingGPUImage DenoisingKnowledge DistillationNetwork Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
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
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Sigmoid Activation 설명 없음

Similar Papers 제목 키워드 기반

Automated Model Compression by Jointly Applied Pruning and Quantization

2020-11-12 · Wenting Tang, Xingxing Wei, Bo Li

In the traditional deep compression framework, iteratively performing network pruning and quantization can reduce the model size and computation cost to meet the deployment requirements. However, such a step-wise applica…

AutoMLModel CompressionNetwork Pruningobject-detection+2

Channel Pruning Guided by Classification Loss and Feature Importance

2020-03-15 · Jinyang Guo, Wanli Ouyang, Dong Xu

In this work, we propose a new layer-by-layer channel pruning method called Channel Pruning guided by classification Loss and feature Importance (CPLI). In contrast to the existing layer-by-layer channel pruning approach…

ClassificationFeature ImportanceGeneral Classification

Multi-Dimensional Pruning: A Unified Framework for Model Compression

2020-06-01 · CVPR 2020 6 · Jinyang Guo, Wanli Ouyang, Dong Xu

In this work, we propose a unified model compression framework called Multi-Dimensional Pruning (MDP) to simultaneously compress the convolutional neural networks (CNNs) on multiple dimensions. In contrast to the existin…

Model Compression

Conditional Automated Channel Pruning for Deep Neural Networks

2020-09-21 · Yixin Liu, Yong Guo, Zichang Liu, Haohua Liu 외

Model compression aims to reduce the redundancy of deep networks to obtain compact models. Recently, channel pruning has become one of the predominant compression methods to deploy deep models on resource-constrained dev…

Model Compression

Channel Pruning via Multi-Criteria based on Weight Dependency

2020-11-06 · Yangchun Yan, Rongzuo Guo, Chao Li, Kang Yang 외

Channel pruning has demonstrated its effectiveness in compressing ConvNets. In many related arts, the importance of an output feature map is only determined by its associated filter. However, these methods ignore a small…

image-classificationImage Classification