Abstract
Recently, channel pruning methods search for the optimal channel numbers by training a weight-sharing network to evaluate architectures of subnetworks. However, the weight shared between subnetworks incurs severe evaluation bias and an accuracy drop. In this paper, we provide a comprehensive understanding of the search space’s impact on the evaluation by dissecting the training process of the weight-sharing network analytically. Specifically, it is proved that the sharing weights induce biased noise on gradients, whose magnitude is proportional to the search range of channel numbers and bias is relative to the average channel numbers of the search space. Motivated by the theoretical result, we design a channel pruning method by training a weight-sharing network with search space shrinking. The search space is iteratively shrunk guided by the optimal architecture searched in the weight-sharing network. The reduced search space boosts the accuracy of the evaluation and significantly cuts down the post-processing computation of finetuning. In the end, we demonstrate the superiority of our channel pruning method over state-of-the-art methods with experiments on ImageNet and COCO.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Lin, M., et al.: Hrank: filter pruning using high-rank feature map. In: 2020 IEEE/CVF Conference on Computer Vision, Pattern Recognition (CVPR) (2020)
He, Y., Liu, P., Wang, Z., Hu, Z., Yang, Y.: Filter pruning via geometric median for deep convolutional neural networks acceleration. In: 2019 IEEE/CVF Conference on Computer Vision, Pattern Recognition (CVPR) (2019)
Molchanov, P., Mallya, A., Tyree, S., Frosio, I., Kautz, J.: Importance estimation for neural network pruning. In: 2019 IEEE/CVF Conference on Computer Vision, Pattern Recognition (CVPR) (2019)
Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H.H.: Learning structured sparsity in deep neural networks. In: Advances in Neural Information Processing Systems (2016)
You, Z., Yan, K., Ye, J., Ma, M., Wang, P.: Gate decorator: global filter pruning method for accelerating deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2019)
Wang, J., et al.: Revisiting parameter sharing for automatic neural channel number search. In: Advances in Neural Information Processing Systems (2020)
Chen, Z., Niu, J., Xie, L., Liu, X., Wei, L., Tian, Q.: Network adjustment: channel search guided by flops utilization ratio. In: 2020 IEEE/CVF Conference on Computer Vision, Pattern Recognition (CVPR) (2020)
Liu, Z., et al.: Metapruning: meta learning for automatic neural network channel pruning. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (2019)
Li, B., Wu, B., Su, J., Wang, G.: EagleEye: fast sub-net evaluation for efficient neural network pruning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 639–654. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_38
Yu, J., Huang, T.: Autoslim: towards oneshot architecture search for channel numbers. In: Advances in Neural Information Processing Systems (2019)
Li, X., et al.: Improving one-shot NAS by suppressing the posterior fading. In: 2020 IEEE/CVF Conference on Computer Vision, Pattern Recognition (CVPR) (2020)
Nayman, N., Noy, A., Ridnik, T., Friedman, I., Jin, R., Zelnik-Manor, L.: XNAS: neural architecture search with expert advice. In: Advances in Neural Information Processing Systems (2019)
Fang, M., Wang, Q., Zhong, Z.: Betanas: balanced training and selective drop for neural architecture search (2019)
Hu, Y., et al.: Angle-based search space shrinking for neural architecture search. In: European Conference on Computer Vision (2020)
Pourchot, A., Ducarouge, A., Sigaud, O.: To share or not to share: a comprehensive appraisal of weight-sharing (2020)
Ding, X., Ding, G., Guo, Y., Han, J., Yan, C.: Approximated oracle filter pruning for destructive CNN width optimization. In: International Conference on Machine Learning (2019)
Joo, D., Yi, E., Baek, S., Kim, J.: Linearly replaceable filters for deep network channel pruning. In: The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-2021) (2021)
Li, Y., et al.: Towards compact CNNs via collaborative compression. In: 2021 IEEE/CVF Conference on Computer Vision, Pattern Recognition (CVPR) (2021)
Guo, S., Wang, Y., Li, Q., Yan, J.: DMCP: differentiable Markov channel pruning for neural networks. In: 2020 IEEE/CVF Conference on Computer Vision, Pattern Recognition (CVPR) (2020)
Su, X., You, S., Wang, F., Qian, C., Zhang, C., Xu, C.: BCNet: searching for network width with bilaterally coupled network. In: 2021 IEEE/CVF Conference on Computer Vision, Pattern Recognition (CVPR) (2021)
Yu, J., Yang, L., Xu, N., Yang, J., Huang, T.S.: Slimmable neural networks. In: International Conference on Learning Representations (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, Z., Li, Z. (2022). Efficient Channel Pruning via Architecture-Guided Search Space Shrinking. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13534. Springer, Cham. https://doi.org/10.1007/978-3-031-18907-4_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-18907-4_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18906-7
Online ISBN: 978-3-031-18907-4
eBook Packages: Computer ScienceComputer Science (R0)