paper-with-me

홈 › Papers

Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization

2022-06-02 · Yanyu Li, Pu Zhao, Geng Yuan, Xue Lin, Yanzhi Wang, Xin Chen

Neural architecture search (NAS) and network pruning are widely studied efficient AI techniques, but not yet perfect. NAS performs exhaustive candidate architecture search, incurring tremendous search cost. Though (structured) pruning can simply shrink model dimension, it remains unclear how to decide the per-layer sparsity automatically and optimally. In this work, we revisit the problem of layer-width optimization and propose Pruning-as-Search (PaS), an end-to-end channel pruning method to search out desired sub-network automatically and efficiently. Specifically, we add a depth-wise binary convolution to learn pruning policies directly through gradient descent. By combining the structural reparameterization and PaS, we successfully searched out a new family of VGG-like and lightweight networks, which enable the flexibility of arbitrary width with respect to each layer instead of each stage. Experimental results show that our proposed architecture outperforms prior arts by around $1.0\%$ top-1 accuracy under similar inference speed on ImageNet-1000 classification task. Furthermore, we demonstrate the effectiveness of our width search on complex tasks including instance segmentation and image translation. Code and models are released.

📄 PDF Abstract BibTeX arXiv:2206.01198

Code (1)

liyy201912/PaS pytorch

Tasks

Instance SegmentationNetwork PruningNeural Architecture SearchSemantic Segmentation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
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…

Similar Papers 제목 키워드 기반

DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search

2020-11-04 · Yushuo Guan, Ning Liu, Pengyu Zhao, Zhengping Che 외

The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment. Structured (channel) pruning is usually applied to reduce t…

Neural Architecture Search

Network Pruning via Transformable Architecture Search

2019-05-23 · NeurIPS 2019 12 · Xuanyi Dong, Yi Yang

Network pruning reduces the computation costs of an over-parameterized network without performance damage. Prevailing pruning algorithms pre-define the width and depth of the pruned networks, and then transfer parameters…

Knowledge DistillationNetwork PruningNeural Architecture SearchTransfer Learning

Revisiting Random Channel Pruning for Neural Network Compression

2022-05-11 · CVPR 2022 1 · Yawei Li, Kamil Adamczewski, Wen Li, Shuhang Gu 외

Channel (or 3D filter) pruning serves as an effective way to accelerate the inference of neural networks. There has been a flurry of algorithms that try to solve this practical problem, each being claimed effective in so…

Neural Network Compression

AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritance

2021-09-14 · Xiangcheng Liu, Jian Cao, Hongyi Yao, Wenyu Sun 외

Channel pruning is one of the major compression approaches for deep neural networks. While previous pruning methods have mostly focused on identifying unimportant channels, channel pruning is considered as a special case…

image-classificationImage ClassificationNeural Architecture Search

MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning

2019-03-25 · ICCV 2019 10 · Zechun Liu, Haoyuan Mu, Xiangyu Zhang, Zichao Guo 외

In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generate weight parameters for an…

AutoMLMeta-Learning