DMCP: Differentiable Markov Channel Pruning for Neural Networks

• URL: http://arxiv.org/abs/2005.03354v2
• Date: Fri, 8 May 2020 03:41:52 GMT
• Title: DMCP: Differentiable Markov Channel Pruning for Neural Networks
• Authors: Shaopeng Guo and Yujie Wang and Quanquan Li and Junjie Yan
• Abstract summary: We propose a novel differentiable method for channel pruning, named Differentiable Markov Channel Pruning (DMCP) Our method is differentiable and can be directly optimized by gradient descent with respect to standard task loss and budget regularization. To validate the effectiveness of our method, we perform extensive experiments on Imagenet with ResNet and MobilenetV2.
• Score: 67.51334229530273
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent works imply that the channel pruning can be regarded as searching optimal sub-structure from unpruned networks. However, existing works based on this observation require training and evaluating a large number of structures, which limits their application. In this paper, we propose a novel differentiable method for channel pruning, named Differentiable Markov Channel Pruning (DMCP), to efficiently search the optimal sub-structure. Our method is differentiable and can be directly optimized by gradient descent with respect to standard task loss and budget regularization (e.g. FLOPs constraint). In DMCP, we model the channel pruning as a Markov process, in which each state represents for retaining the corresponding channel during pruning, and transitions between states denote the pruning process. In the end, our method is able to implicitly select the proper number of channels in each layer by the Markov process with optimized transitions. To validate the effectiveness of our method, we perform extensive experiments on Imagenet with ResNet and MobilenetV2. Results show our method can achieve consistent improvement than state-of-the-art pruning methods in various FLOPs settings. The code is available at https://github.com/zx55/dmcp

Related papers

• Network Pruning via Feature Shift Minimization [8.593369249204132]
  We propose a novel Feature Shift Minimization (FSM) method to compress CNN models, which evaluates the feature shift by converging the information of both features and filters. The proposed method yields state-of-the-art performance on various benchmark networks and datasets, verified by extensive experiments.
  arXiv  Detail & Related papers  (2022-07-06T12:50:26Z)
• Revisiting Random Channel Pruning for Neural Network Compression [159.99002793644163]
  Channel (or 3D filter) pruning serves as an effective way to accelerate the inference of neural networks. In this paper, we try to determine the channel configuration of the pruned models by random search. We show that this simple strategy works quite well compared with other channel pruning methods.
  arXiv  Detail & Related papers  (2022-05-11T17:59:04Z)
• AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritance [9.3421559369389]
  We propose a pruning framework that adaptively determines the number of each layer's channels as well as the wights inheritance criteria for sub-network. AdaPruner allows to obtain pruned network quickly, accurately and efficiently. On ImageNet, we reduce 32.8% FLOPs of MobileNetV2 with only 0.62% decrease for top-1 accuracy, which exceeds all previous state-of-the-art channel pruning methods.
  arXiv  Detail & Related papers  (2021-09-14T01:52:05Z)
• Channel-wise Knowledge Distillation for Dense Prediction [73.99057249472735]
  We propose to align features channel-wise between the student and teacher networks. We consistently achieve superior performance on three benchmarks with various network structures.
  arXiv  Detail & Related papers  (2020-11-26T12:00:38Z)
• Operation-Aware Soft Channel Pruning using Differentiable Masks [51.04085547997066]
  We propose a data-driven algorithm, which compresses deep neural networks in a differentiable way by exploiting the characteristics of operations. We perform extensive experiments and achieve outstanding performance in terms of the accuracy of output networks.
  arXiv  Detail & Related papers  (2020-07-08T07:44:00Z)
• Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio [101.84651388520584]
  This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-06T15:51:00Z)
• Channel Pruning via Automatic Structure Search [109.83642249625098]
  We propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner. ABCPruner has been demonstrated to be more effective, which also enables the fine-tuning to be conducted efficiently in an end-to-end manner.
  arXiv  Detail & Related papers  (2020-01-23T14:51:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.