Abstract
This paper aims to explore the feasibility of neural architecture search (NAS) given only a pre-trained model without using any original training data. This is an important circumstance for privacy protection, bias avoidance, etc., in real-world scenarios. To achieve this, we start by synthesizing usable data through recovering the knowledge from a pre-trained deep neural network. Then we use the synthesized data and their predicted soft labels to guide NAS. We identify that the quality of the synthesized data will substantially affect the NAS results. Particularly, we find NAS requires the synthesized images to possess enough semantics, diversity, and a minimal domain gap from the natural images. To meet these requirements, we propose recursive label calibration to encode more relative semantics in images, as well as regional update strategy to enhance the diversity. Further, we use input and feature-level regularization to mimic the original data distribution in latent space and reduce the domain gap. We instantiate our proposed framework with three popular NAS algorithms: DARTS, ProxylessNAS and SPOS. Surprisingly, our results demonstrate that the architectures discovered by searching with our synthetic data achieve accuracy that is comparable to, or even higher than, architectures discovered by searching from the original ones, for the first time, deriving the conclusion that NAS can be done effectively with no need of access to the original or called natural data if the synthesis method is well designed. Code and models are available at: https://github.com/liuzechun/Data-Free-NAS.
This work is done when Zechun Liu is an intern at Google Research.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. arXiv preprint arXiv:1611.02167 (2016)
Brock, A., Donahue, J., Simonyan, K., et al.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)
Brock, A., Lim, T., Ritchie, J.M., Weston, N.: SMASH: one-shot model architecture search through hypernetworks. arXiv preprint arXiv:1708.05344 (2017)
Cai, H., Zhu, L., Han, S., et al.: ProxylessNAS: direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332 (2018)
Chen, H., et al.: Data-free learning of student networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3514–3522 (2019)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on CVPR, pp. 1251–1258 (2017)
Dai, X., et al.: ChamNet: towards efficient network design through platform-aware model adaptation. arXiv preprint arXiv:1812.08934 (2018)
Guo, Z., et al.: Single path one-shot neural architecture search with uniform sampling. arXiv preprint arXiv:1904.00420 (2019)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Jin, H., Song, Q., Hu, X.: Efficient neural architecture search with network morphism. arXiv preprint arXiv:1806.10282 (2018)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)
Liu, C., Dollár, P., He, K., Girshick, R., Yuille, A., Xie, S.: Are labels necessary for neural architecture search? arXiv preprint arXiv:2003.12056 (2020)
Liu, C., et al.: Progressive neural architecture search. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 19–35. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_2
Liu, H., Simonyan, K., Yang, Y., et al.: DARTS: differentiable architecture search. In: International Conference on Learning Representations (2019)
Liu, Z., et al.: MetaPruning: meta learning for automatic neural network channel pruning. In: Proceedings of ICCV, pp. 3296–3305 (2019)
Mordvintsev, A., Olah, C., Tyka, M., et al.: Inceptionism: going deeper into neural networks (2015)
Müller, R., Kornblith, S., Hinton, G.: When does label smoothing help? In: NeurIPS (2019)
Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:1802.03268 (2018)
Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. arXiv preprint arXiv:1802.01548 (2018)
Real, E., et al.: Large-scale evolution of image classifiers. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2902–2911. JMLR.org (2017)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Shen, Z., He, Z., Xue, X.: MEAL: multi-model ensemble via adversarial learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4886–4893 (2019)
Shen, Z., Liu, Z., Xu, D., Chen, Z., Cheng, K.T., Savvides, M.: Is label smoothing truly incompatible with knowledge distillation: an empirical study. In: International Conference on Learning Representations (2021)
Spearman, C.: The proof and measurement of association between two things (1961)
Tan, M., Chen, B., Pang, R., Vasudevan, V., Le, Q.V.: MnasNet: platform-aware neural architecture search for mobile. arXiv preprint arXiv:1807.11626 (2018)
Wu, B., et al.: FBNet: hardware-aware efficient convnet design via differentiable neural architecture search. arXiv preprint arXiv:1812.03443 (2018)
Xu, S., et al.: Generative low-bitwidth data free quantization. arXiv preprint arXiv:2003.03603 (2020)
Yin, H., et al.: Dreaming to distill: data-free knowledge transfer via deepinversion. In: Proceedings of the CVPR, pp. 8715–8724 (2020)
Ying, C., Klein, A., Christiansen, E., Real, E., Murphy, K., Hutter, F.: NAS-Bench-101: towards reproducible neural architecture search. In: International Conference on Machine Learning, pp. 7105–7114 (2019)
Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848–6856 (2018)
Zhong, Z., et al.: BlockQNN: efficient block-wise neural network architecture generation. arXiv preprint arXiv:1808.05584 (2018)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017)
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710 (2018)
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
Liu, Z., Shen, Z., Long, Y., Xing, E., Cheng, KT., Leichner, C. (2022). Data-Free Neural Architecture Search via Recursive Label Calibration. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13684. Springer, Cham. https://doi.org/10.1007/978-3-031-20053-3_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-20053-3_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20052-6
Online ISBN: 978-3-031-20053-3
eBook Packages: Computer ScienceComputer Science (R0)