MatchNAS: Optimizing Edge AI in Sparse-Label Data Contexts via Automating Deep Neural Network Porting for Mobile Deployment
Pages 2965 - 2975
Abstract
Recent years have seen the explosion of edge intelligence with powerful Deep Neural Networks (DNNs). One popular scheme is training DNNs on powerful cloud servers and subsequently porting them to mobile devices after being lightweight. Conventional approaches manually specialized DNNs for various edge platforms and retrain them with real-world data. However, as the number of platforms increases, these approaches become labour-intensive and computationally prohibitive. Additionally, real-world data tends to be sparse-label, further increasing the difficulty of lightweight models. In this paper, we propose MatchNAS, a novel scheme for porting DNNs to mobile devices. Specifically, we simultaneously optimise a large network family using both labelled and unlabelled data and then automatically search for tailored networks for different hardware platforms. MatchNAS acts as an intermediary that bridges the gap between cloud-based DNNs and edge-based DNNs.
Supplemental Material
MP4 File
Supplemental video
- Download
- 24.87 MB
References
[1]
Philip Bachman, Ouais Alsharif, and Doina Precup. 2014. Learning with Pseudo-Ensembles. In NIPS. https://api.semanticscholar.org/CorpusID:8307266
[2]
Bowen Baker, Otkrist Gupta, Nikhil Naik, and Ramesh Raskar. 2016. Designing neural network architectures using reinforcement learning. arXiv preprint arXiv:1611.02167 (2016).
[3]
David Berthelot, Nicholas Carlini, Ekin Dogus Cubuk, Alexey Kurakin, Kihyuk Sohn, Han Zhang, and Colin Raffel. 2020. ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring. In International Conference on Learning Representations. https://api.semanticscholar.org/CorpusID:213757781
[4]
David Berthelot, Nicholas Carlini, Ian J. Goodfellow, Nicolas Papernot, Avital Oliver, and Colin Raffel. 2019. MixMatch: A Holistic Approach to Semi-Supervised Learning. ArXiv, Vol. abs/1905.02249 (2019). https://api.semanticscholar.org/CorpusID:146808485
[5]
Han Cai, Chuang Gan, and Song Han. 2019. Once for All: Train One Network and Specialize it for Efficient Deployment. ArXiv, Vol. abs/1908.09791 (2019). https://api.semanticscholar.org/CorpusID:201666112
[6]
Han Cai, Ligeng Zhu, and Song Han. 2018. ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. ArXiv, Vol. abs/1812.00332 (2018). https://api.semanticscholar.org/CorpusID:54438210
[7]
Wuyang Chen, Xinyu Gong, and Zhangyang Wang. 2021. Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective. ArXiv, Vol. abs/2102.11535 (2021). https://api.semanticscholar.org/CorpusID:232013680
[8]
Xiaoliang Dai, Peizhao Zhang, Bichen Wu, Hongxu Yin, Fei Sun, Yanghan Wang, Marat Dukhan, Yunqing Hu, Yiming Wu, Yangqing Jia, Péter Vajda, Matthew Uyttendaele, and Niraj Kumar Jha. 2018. ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018), 11390--11399. https://api.semanticscholar.org/CorpusID:56657862
[9]
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, K. Li, and Li Fei-Fei. 2009. ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition (2009), 248--255. https://api.semanticscholar.org/CorpusID:57246310
[10]
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. ArXiv, Vol. abs/1810.04805 (2019). https://api.semanticscholar.org/CorpusID:52967399
[11]
Zeqian Dong, Qiang He, Feifei Chen, Hai Jin, Tao Gu, and Yun Yang. 2023. EdgeMove: Pipelining Device-Edge Model Training for Mobile Intelligence. Proceedings of the ACM Web Conference 2023 (2023). https://api.semanticscholar.org/CorpusID:258333779
[12]
M. Everingham, S. M. A. Eslami, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. 2015. The Pascal Visual Object Classes Challenge: A Retrospective. International Journal of Computer Vision, Vol. 111, 1 (Jan. 2015), 98--136.
[13]
A. Gordon, Elad Eban, Ofir Nachum, Bo Chen, Tien-Ju Yang, and E. Choi. 2017. MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2017), 1586--1595. https://api.semanticscholar.org/CorpusID:206596875
[14]
Zichao Guo, Xiangyu Zhang, Haoyuan Mu, Wen Heng, Zechun Liu, Yichen Wei, and Jian Sun. 2019. Single Path One-Shot Neural Architecture Search with Uniform Sampling. In European Conference on Computer Vision. https://api.semanticscholar.org/CorpusID:90262841
[15]
Samira Hayat, Roland Jung, Hermann Hellwagner, Christian Bettstetter, Driton Emini, and Dominik Schnieders. 2021. Edge Computing in 5G for Drone Navigation: What to Offload? IEEE Robotics and Automation Letters, Vol. 6, 2 (2021), 2571--2578. https://doi.org/10.1109/LRA.2021.3062319
[16]
Kaiming He, X. Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015), 770--778. https://api.semanticscholar.org/CorpusID:206594692
[17]
Geoffrey E. Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. ArXiv, Vol. abs/1503.02531 (2015).
[18]
Andrew G. Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc V. Le, and Hartwig Adam. 2019. Searching for MobileNetV3. 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (2019), 1314--1324. https://api.semanticscholar.org/CorpusID:146808333
[19]
Jonathan Krause, Michael Stark, Jia Deng, and Li Fei-Fei. 2013. 3D Object Representations for Fine-Grained Categorization. 2013 IEEE International Conference on Computer Vision Workshops (2013), 554--561. https://api.semanticscholar.org/CorpusID:14342571
[20]
Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. https://api.semanticscholar.org/CorpusID:18268744
[21]
Dong-Hyun Lee. 2013. Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. https://api.semanticscholar.org/CorpusID:18507866
[22]
Ming Lin, Pichao Wang, Zhenhong Sun, Hesen Chen, Xiuyu Sun, Qi Qian, Hao Li, and Rong Jin. 2021. Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition. 2021 IEEE/CVF International Conference on Computer Vision (ICCV) (2021), 337--346. https://api.semanticscholar.org/CorpusID:245835451
[23]
Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. In International Conference on Learning Representations. https://api.semanticscholar.org/CorpusID:53592270
[24]
Miranda. McClellan, Cristina Cervelló-Pastor, and Sebastià Sallent. 2020. Deep Learning at the Mobile Edge: Opportunities for 5G Networks. Applied Sciences (2020). https://api.semanticscholar.org/CorpusID:225525817
[25]
Geoffrey J. McLachlan. 1975. Iterative Reclassification Procedure for Constructing An Asymptotically Optimal Rule of Allocation in Discriminant-Analysis. J. Amer. Statist. Assoc., Vol. 70 (1975), 365--369. https://api.semanticscholar.org/CorpusID:120764023
[26]
Joseph Charles Mellor, Jack Turner, Amos J. Storkey, and Elliot J. Crowley. 2020. Neural Architecture Search without Training. ArXiv, Vol. abs/2006.04647 (2020). https://api.semanticscholar.org/CorpusID:219531078
[27]
Maad M. Mijwil. 2022. Has the Future Started? The Current Growth of Artificial Intelligence, Machine Learning, and Deep Learning. Iraqi Journal for Computer Science and Mathematics (2022). https://api.semanticscholar.org/CorpusID:249688145
[28]
Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017).
[29]
Esteban Real, Sherry Moore, Andrew Selle, Saurabh Saxena, Yutaka Leon Suematsu, Jie Tan, Quoc V. Le, and Alexey Kurakin. 2017. Large-Scale Evolution of Image Classifiers. ArXiv, Vol. abs/1703.01041 (2017).
[30]
Manas Sahni, Shreya Varshini, Alind Khare, and Alexey Tumanov. 2021. CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment. ArXiv, Vol. abs/2104.12642 (2021). https://api.semanticscholar.org/CorpusID:232286427
[31]
Samsung. [n.,d.]. Samsung Remote Test Lab. https://developer.samsung.com/remote-test-lab
[32]
Christian Sciuto, Kaicheng Yu, Martin Jaggi, Claudiu Cristian Musat, and Mathieu Salzmann. 2019. Evaluating the Search Phase of Neural Architecture Search. ArXiv, Vol. abs/1902.08142 (2019).
[33]
Kihyuk Sohn, David Berthelot, Chun-Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin Dogus Cubuk, Alexey Kurakin, Han Zhang, and Colin Raffel. 2020. FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence. ArXiv, Vol. abs/2001.07685 (2020). https://api.semanticscholar.org/CorpusID:210839228
[34]
Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, and Quoc V. Le. 2018. MnasNet: Platform-Aware Neural Architecture Search for Mobile. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018), 2815--2823. https://api.semanticscholar.org/CorpusID:51891697
[35]
Antti Tarvainen and Harri Valpola. 2017. Weight-averaged consistency targets improve semi-supervised deep learning results. ArXiv, Vol. abs/1703.01780 (2017). https://api.semanticscholar.org/CorpusID:2759724
[36]
C. Wah, S. Branson, P. Welinder, P. Perona, and S. Belongie. 2011. Technical Report CNS-TR-2011-001. California Institute of Technology.
[37]
Dilin Wang, Meng Li, Chengyue Gong, and Vikas Chandra. 2021. AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 6414--6423.
[38]
Qizhe Xie, Zihang Dai, Eduard H. Hovy, Minh-Thang Luong, and Quoc V. Le. 2019. Unsupervised Data Augmentation for Consistency Training. arXiv: Learning (2019). https://api.semanticscholar.org/CorpusID:195873898
[39]
Mengwei Xu, Jiawei Liu, Yuanqiang Liu, Felix Xiaozhu Lin, Yunxin Liu, and Xuanzhe Liu. 2018. A First Look at Deep Learning Apps on Smartphones. The World Wide Web Conference (2018). https://api.semanticscholar.org/CorpusID:59158795
[40]
Shan You, Tao Huang, Mingmin Yang, Fei Wang, Chen Qian, and Changshui Zhang. 2020. GreedyNAS: Towards Fast One-Shot NAS With Greedy Supernet. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020), 1996--2005.
[41]
Jiahui Yu, Pengchong Jin, Hanxiao Liu, Gabriel Bender, Pieter-Jan Kindermans, Mingxing Tan, Thomas Huang, Xiaodan Song, and Quoc V. Le. 2020. BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models. In ECCV.
[42]
Rui Zhao, Ruqiang Yan, Zhenghua Chen, Kezhi Mao, Peng Wang, and Robert X. Gao. 2019. Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing (2019). https://api.semanticscholar.org/CorpusID:125608550
[43]
Barret Zoph and Quoc V Le. 2016. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016).
[44]
Barret Zoph, Vijay Vasudevan, Jonathon Shlens, and Quoc V. Le. 2018. Learning Transferable Architectures for Scalable Image Recognition. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018), 8697--8710.
Index Terms
- MatchNAS: Optimizing Edge AI in Sparse-Label Data Contexts via Automating Deep Neural Network Porting for Mobile Deployment
Recommendations
Edge-preserving image denoising using a deep convolutional neural network
Highlights- This paper makes use of a deep CNN for image denoising.
- The network is trained ...
AbstractThis paper introduces a novel denoising approach making use of a deep convolutional neural network to preserve image edges. The network is trained by using the edge map obtained from the well-known Canny algorithm and aims at ...
SAR image edge detection via sparse representation
In this paper, we propose a new synthetic aperture radar (SAR) image detection algorithm based on the de-noising algorithm via the sparse representation and a new morphology edge detector. Firstly, we apply the Shearlet transform to the SAR image to get ...
Deep Label Distribution Learning With Label Ambiguity
Convolutional neural networks (ConvNets) have achieved excellent recognition performance in various visual recognition tasks. A large labeled training set is one of the most important factors for its success. However, it is difficult to collect ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
May 2024
4826 pages
ISBN:9798400701719
DOI:10.1145/3589334
- General Chairs:
- Tat-Seng Chua,
- Chong-Wah Ngo,
- Proceedings Chair:
- Roy Ka-Wei Lee,
- Program Chairs:
- Ravi Kumar,
- Hady W. Lauw
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 13 May 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
WWW '24
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,899 of 8,196 submissions, 23%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 59Total Downloads
- Downloads (Last 12 months)59
- Downloads (Last 6 weeks)17
Reflects downloads up to 03 Oct 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in