paper-with-me

Papers

Blending Pruning Criteria for Convolutional Neural Networks

2021-07-11 · wei he, Zhongzhan Huang, Mingfu Liang, Senwei Liang, Haizhao Yang

The advancement of convolutional neural networks (CNNs) on various vision applications has attracted lots of attention. Yet the majority of CNNs are unable to satisfy the strict requirement for real-world deployment. To overcome this, the recent popular network pruning is an effective method to reduce the redundancy of the models. However, the ranking of filters according to their "importance" on different pruning criteria may be inconsistent. One filter could be important according to a certain criterion, while it is unnecessary according to another one, which indicates that each criterion is only a partial view of the comprehensive "importance". From this motivation, we propose a novel framework to integrate the existing filter pruning criteria by exploring the criteria diversity. The proposed framework contains two stages: Criteria Clustering and Filters Importance Calibration. First, we condense the pruning criteria via layerwise clustering based on the rank of "importance" score. Second, within each cluster, we propose a calibration factor to adjust their significance for each selected blending candidates and search for the optimal blending criterion via Evolutionary Algorithm. Quantitative results on the CIFAR-100 and ImageNet benchmarks show that our framework outperforms the state-of-the-art baselines, regrading to the compact model performance after pruning.

📄 PDF Abstract BibTeX arXiv:2107.05033

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringNetwork Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning

2020-04-24 · Zhongzhan Huang, Wenqi Shao, Xinjiang Wang, Liang Lin 외

Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), where various pruning criteria have been proposed to remove the redundant filters. From our comprehensive experiments, we found…

Rethinking the Pruning Criteria for Convolutional Neural Network

2021-01-01 · NeurIPS 2021 12 · Zhongzhan Huang, Xinjiang Wang, Ping Luo

Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), and various pruning criteria have been proposed to remove the redundant filters of CNNs. From our comprehensive experiments, we…

Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration

2020-06-01 · CVPR 2020 6 · Yang He, Yuhang Ding, Ping Liu, Linchao Zhu 외

Filter pruning has been widely applied to neural network compression and acceleration. Existing methods usually utilize pre-defined pruning criteria, such as Lp-norm, to prune unimportant filters. There are two major lim…

image-classificationImage ClassificationNeural Network Compression

Pruning Convolutional Neural Networks for Resource Efficient Inference

2016-11-19 · Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila 외

We propose a new formulation for pruning convolutional kernels in neural networks to enable efficient inference. We interleave greedy criteria-based pruning with fine-tuning by backpropagation - a computationally efficie…

Transfer Learning

WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networks

2023-02-16 · Shaowu Chen, Weize Sun, Lei Huang

Filter pruning has attracted increasing attention in recent years for its capacity in compressing and accelerating convolutional neural networks. Various data-independent criteria, including norm-based and relationship-b…

ClassificationNetwork PruningNeural Network Compression