CAM-NAS: An Efficient and Interpretable Neural Architecture Search Model Based on Class Activation Mapping
Abstract
:1. Introduction
2. Related Works
2.1. Neural Architecture Search
2.2. Class Activation Map
3. Method
3.1. Main Process
3.2. CAM Techniques
3.3. Mathematical Equation for the Main Processes
Algorithm 1: CAM-NAS |
Require: Search space S, inference budget B, maximal depth L, total number of
iterations T, evolutionary population size N, initial structure .
|
3.4. CAM-NAS Algorithm
4. Experiment
4.1. Model Selection Process
4.2. Illustration of an Example
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
AI | artificial intelligence |
CNN | convolutional neural network |
NAS | neural architecture search |
ENAS | efficient neural architecture search |
CAM | class activation map |
CAM-NAS | class activation map-based neural architecture search |
GAP | global average pooling |
XGradCAM | axiom-based Grad-CAM |
References
- Sun, Y.; Xue, B.; Zhang, M.; Yen, G.G. Evolving deep convolutional neural networks for image classification. IEEE Trans. Evol. Comput. 2019, 24, 394–407. [Google Scholar] [CrossRef]
- Ang, K.M.; El-kenawy, E.S.M.; Abdelhamid, A.A.; Ibrahim, A.; Alharbi, A.H.; Khafaga, D.S.; Tiang, S.S.; Lim, W.H. Optimal Design of Convolutional Neural Network Architectures Using Teaching–Learning-Based Optimization for Image Classification. Symmetry 2022, 14, 2323. [Google Scholar] [CrossRef]
- Ashraf, S.; Ahmed, T. Dual-nature biometric recognition epitome. Trends Comput. Sci. Inf. Technol. 2020, 5, 8–14. [Google Scholar]
- Fernandes, F.E.; Yen, G.G. Automatic searching and pruning of deep neural networks for medical imaging diagnostic. IEEE Trans. Neural Netw. Learn. Syst. 2020, 32, 5664–5674. [Google Scholar] [CrossRef] [PubMed]
- Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Huang, G.; Liu, Z.; Van Der Maaten, L.; Weinberger, K.Q. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 4700–4708. [Google Scholar]
- Xue, Y.; Wang, Y.; Liang, J.; Slowik, A. A self-adaptive mutation neural architecture search algorithm based on blocks. IEEE Comput. Intell. Mag. 2021, 16, 67–78. [Google Scholar] [CrossRef]
- Zoph, B.; Le, Q.V. Neural architecture search with reinforcement learning. In Proceedings of the 5th International Conference on Learning Representations, Toulon, France, 24–26 April 2017. [Google Scholar]
- Zoph, B.; Vasudevan, V.; Shlens, J.; Len, Q.V. Learning transferable architectures for scalable image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 8697–8710. [Google Scholar]
- Pham, H.; Guan, M.; Zoph, B.; Le, Q.; Dean, J. Efficient neural architecture search via parameters sharing. In Proceedings of the International Conference on Machine Learning, Stockholm, Sweden, 10–15 July 2018; pp. 4095–4104. [Google Scholar]
- Liu, H.; Simonyan, K.; Yang, Y. Darts: Differentiable architecture search. arXiv 2018, arXiv:1806.09055. [Google Scholar]
- Chen, W.; Gong, X.; Wang, Z. Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective. In Proceedings of the International Conference on Learning Representations, Addis Ababa, Ethiopia, 26–30 April 2020. [Google Scholar]
- Mellor, J.; Turner, J.; Storkey, A.; Crowley, E.J. Neural architecture search without training. In Proceedings of the International Conference on Machine Learning, Virtual, 18–24 July 2021; pp. 7588–7598. [Google Scholar]
- Lin, M.; Wang, P.; Sun, Z.; Chen, H.; Sun, X.; Qian, Q.; Li, H.; Jin, R. Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada, 10–17 October 2021; pp. 347–356. [Google Scholar]
- Zhou, B.; Khosla, A.; Lapedriza, A.; Oliva, A.; Torralba, A. Learning deep features for discriminative localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 2921–2929. [Google Scholar]
- Selvaraju, R.R.; Cogswell, M.; Das, A.; Vedantam, R.; Parikh, D.; Batra, D. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. In Proceedings of the Computer Vision (ICCV), IEEE International Conference, Venice, Italy, 22–29 October 2017; pp. 618–626. [Google Scholar]
- Chattopadhay, A.; Sarkar, A.; Howlader, P.; Balasubramanian, V.N. Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks. In Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NA, USA, 12–15 March 2018; pp. 839–847. [Google Scholar]
- Wang, H.; Wang, Z.; Du, M.; Yang, F.; Zhang, Z.; Ding, S.; Mardziel, P.; Hu, X. Score-CAM: Score-weighted visual explanations for convolutional neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA, 14–19 June 2020; pp. 24–25. [Google Scholar]
- Wang, H.; Naidu, R.; Michael, J.; Kundu, S.S. SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization. arXiv 2020, arXiv:2006.14255. [Google Scholar]
- Naidu, R.; Ghosh, A.; Maurya, Y.; Kundu, S.S. IS-CAM: Integrated Score-CAM for axiomatic-based explanations. arXiv 2020, arXiv:2010.03023. [Google Scholar]
- Omeiza, D.; Speakman, S.; Cintas, C.; Weldermariam, K. Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models. arXiv 2019, arXiv:1908.01224. [Google Scholar]
- Fu, R.; Hu, Q.; Dong, X.; Guo, Y.; Gao, Y.; Li, B. Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs. arXiv 2020, arXiv:2008.02312. [Google Scholar]
Related Works | Deficiencies |
---|---|
NASNet | Requires expensive hardware facilities and time, is prone to over-fitting, is usually optimized for specific tasks and datasets, finds optimal architectures that may not be applicable to other types of tasks, and needs to be researched or fine-tuned. |
ENAS | Limited to specific tasks and requires multiple reinforcement learning training; the search process requires time and a large amount of computational resources. |
DARTS | Searches only one layer of the network structure, cannot search deeper network structures, easy to overfit. |
TE-NAS | Uses a genetic algorithm for search; has poor performance in high-dimensional search spaces and low search efficiency. |
Zen-NAS | Can be affected by the limitations of the pre-trained model; the pre-trained architecture may not generalize well to the target task, thus affecting performance. |
Proxy | CIFAR-10 | CIFAR-100 |
---|---|---|
Zen-Score | 96.2% | 80.1% |
FLOPs | 93.1% | 64.7% |
Grad | 92.8% | 65.4% |
Synflow | 95.1% | 75.9% |
TE-Score | 96.1% | 77.2% |
NASWOT | 96.0% | 77.5% |
Random | 93.5 ± 0.7% | 71.1 ± 3.1% |
CAM-NAS | 95.68% | 75.94% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, Z.; Wang, Z.; Joe, I. CAM-NAS: An Efficient and Interpretable Neural Architecture Search Model Based on Class Activation Mapping. Appl. Sci. 2023, 13, 9686. https://doi.org/10.3390/app13179686
Zhang Z, Wang Z, Joe I. CAM-NAS: An Efficient and Interpretable Neural Architecture Search Model Based on Class Activation Mapping. Applied Sciences. 2023; 13(17):9686. https://doi.org/10.3390/app13179686
Chicago/Turabian StyleZhang, Zhiyuan, Zhan Wang, and Inwhee Joe. 2023. "CAM-NAS: An Efficient and Interpretable Neural Architecture Search Model Based on Class Activation Mapping" Applied Sciences 13, no. 17: 9686. https://doi.org/10.3390/app13179686
APA StyleZhang, Z., Wang, Z., & Joe, I. (2023). CAM-NAS: An Efficient and Interpretable Neural Architecture Search Model Based on Class Activation Mapping. Applied Sciences, 13(17), 9686. https://doi.org/10.3390/app13179686