RS-DARTS: A Convolutional Neural Architecture Search for Remote Sensing Image Scene Classification
Abstract
:1. Introduction
2. Related Works
2.1. CNN-Based Methods
2.2. NAS Methods
3. The Proposed Method
3.1. Preliminary: DARTS
3.2. Remote Sensing DARTS for Scene Classfication
3.2.1. Collaboration Mechanism and Binarization of Structural Parameters
3.2.2. Adding Noise in Skip-Connection
3.2.3. Sample 1/K of All Channels into Mixed Computation
Algorithm 1 Remote Sensing DARTS for Scene Classification algorithm |
|
4. Experiments
4.1. Datasets Description
4.2. A Metric for Evaluation
4.3. Prepared Data Sets
4.4. Implementation Details
5. Results and Analysis
5.1. Compared with CNN Models
5.2. Compared with Other NAS Methods
5.3. Searched the Cell’s Result
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Cheriyadat, A.M. Unsupervised Feature Learning for Aerial Scene Classification. IEEE Trans. Geosci. Remote Sens. 2014, 52, 439–451. [Google Scholar] [CrossRef]
- Hu, F.; Xia, G.-S.; Hu, J.; Zhang, L. Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery. Remote Sens. 2015, 7, 14680–14707. [Google Scholar] [CrossRef] [Green Version]
- Rogan, J.; Chen, D. Remote sensing technology for mapping and monitoring land-cover and land-use change. Prog. Plan. 2004, 61, 301–325. [Google Scholar] [CrossRef]
- Joint Dictionary Learning for Multispectral Change Detection|IEEE Journals & Magazine|IEEE Xplore. Available online: https://ieeexplore.ieee.org/document/7422756 (accessed on 30 July 2021).
- Nogueira, K.; Penatti, O.A.; dos Santos, J.A. Towards better exploiting convolutional neural networks for remote sensing scene classification. Pattern Recognit. 2017, 61, 539–556. [Google Scholar] [CrossRef] [Green Version]
- Densely Based Multi-Scale and Multi-Modal Fully Convolutional Networks for High-Resolution Remote-Sensing Image Semantic Segmentation|IEEE Journals & Magazine|IEEE Xplore. Available online: https://ieeexplore.ieee.org/abstract/document/8684908 (accessed on 30 July 2021).
- Zhu, X.X.; Tuia, D.; Mou, L.; Xia, G.-S.; Zhang, L.; Xu, F.; Fraundorfer, F. Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources. IEEE Geosci. Remote Sens. Mag. 2017, 5, 8–36. [Google Scholar] [CrossRef] [Green Version]
- A Novel System for Content-Based Retrieval of Single and Multi-Label High-Dimensional Remote Sensing Images|IEEE Journals & Magazine|IEEE Xplore. Available online: https://ieeexplore.ieee.org/document/8391715 (accessed on 30 July 2021).
- Li, Y.; Peng, C.; Chen, Y.; Jiao, L.; Zhou, L.; Shang, R. A Deep Learning Method for Change Detection in Synthetic Aperture Radar Images. IEEE Trans. Geosci. Remote Sens. 2019, 57, 5751–5763. [Google Scholar] [CrossRef]
- Sun, W.; Liu, K.; Ren, G.; Liu, W.; Yang, G.; Meng, X.; Peng, J. A simple and effective spectral-spatial method for mapping large-scale coastal wetlands using China ZY1-02D satellite hyperspectral images. Int. J. Appl. Earth Obs. Geoinf. 2021, 104, 102572. [Google Scholar] [CrossRef]
- Wang, Z.; Du, L.; Zhang, P.; Li, L.; Wang, F.; Xu, S.; Su, H. Visual Attention-Based Target Detection and Discrimination for High-Resolution SAR Images in Complex Scenes. IEEE Trans. Geosci. Remote. Sens. 2017, 56, 1855–1872. [Google Scholar] [CrossRef]
- Ghamisi, P.; Maggiori, E.; Li, S.; Souza, R.; Tarablaka, Y.; Moser, G.; De Giorgi, A.; Fang, L.; Chen, Y.; Chi, M.; et al. New Frontiers in Spectral-Spatial Hyperspectral Image Classification: The Latest Advances Based on Mathematical Morphology, Markov Random Fields, Segmentation, Sparse Representation, and Deep Learning. IEEE Geosci. Remote Sens. Mag. 2018, 6, 10–43. [Google Scholar] [CrossRef]
- Zheng, X.; Yuan, Y.; Lu, X. A Deep Scene Representation for Aerial Scene Classification. IEEE Trans. Geosci. Remote. Sens. 2019, 57, 4799–4809. [Google Scholar] [CrossRef]
- Sun, W.; Ren, K.; Meng, X.; Xiao, C.; Yang, G.; Peng, J. A Band Divide-and-Conquer Multispectral and Hyperspectral Image Fusion Method. IEEE Trans. Geosci. Remote Sens. 2021, 60, 5502113. [Google Scholar] [CrossRef]
- Zhu, Q.; Zhong, Y.; Liu, Y.; Zhang, L.; Li, D. A Deep-Local-Global Feature Fusion Framework for High Spatial Resolution Imagery Scene Classification. Remote. Sens. 2018, 10, 568. [Google Scholar] [CrossRef] [Green Version]
- Yang, Y.; Newsam, S. Bag-of-visual-words and spatial extensions for land-use classification. In Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, San Jose, CA, USA, 3–5 November 2010; pp. 270–279. [Google Scholar] [CrossRef]
- Jiang, Y.; Yuan, J.; Yu, G. Randomized Spatial Partition for Scene Recognition. In Computer Vision–ECCV 2012; Springer: Singapore, 2012; pp. 730–743. [Google Scholar]
- Yang, Y.; Newsam, S. Spatial pyramid co-occurrence for image classification. In Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain, 6–13 November 2011; pp. 1465–1472. [Google Scholar]
- Chen, S.; Tian, Y. Pyramid of Spatial Relatons for Scene-Level Land Use Classification. IEEE Trans. Geosci. Remote Sens. 2015, 53, 1947–1957. [Google Scholar] [CrossRef]
- Li, E.; Xia, J.; Du, P.; Lin, C.; Samat, A. Integrating Multilayer Features of Convolutional Neural Networks for Remote Sensing Scene Classification. IEEE Trans. Geosci. Remote Sens. 2017, 55, 5653–5665. [Google Scholar] [CrossRef]
- Peng, J.; Sun, W.; Li, W.; Li, H.-C.; Meng, X.; Ge, C.; Du, Q. Low-Rank and Sparse Representation for Hyperspectral Image Processing: A Review. IEEE Geosci. Remote Sens. Mag. 2021, 2–35. [Google Scholar] [CrossRef]
- He, K.; Girshick, R.; Dollar, P. Rethinking ImageNet Pre-Training. 2019. Available online: https://openaccess.thecvf.com/content_ICCV_2019/html/He_Rethinking_ImageNet_Pre-Training_ICCV_2019_paper.html (accessed on 1 August 2021).
- 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, Salt Lake City, UT, USA, 18–23 June 2018; pp. 8697–8710. [Google Scholar]
- He, N.; Fang, L.; Li, S.; Plaza, A.; Plaza, J. Remote Sensing Scene Classification Using Multilayer Stacked Covariance Pooling. IEEE Trans. Geosci. Remote. Sens. 2018, 56, 6899–6910. [Google Scholar] [CrossRef]
- Cheng, G.; Han, J.; Lu, X. Remote Sensing Image Scene Classification: Benchmark and State of the Art. Proc. IEEE. 2017, 105, 1865–1883. [Google Scholar] [CrossRef] [Green Version]
- Sánchez, J.; Perronnin, F.; Mensink, T.; Verbeek, J. Image Classification with the Fisher Vector: Theory and Practice. Int. J. Comput. Vis. 2013, 105, 222–245. [Google Scholar] [CrossRef]
- Zhao, W.; Du, S. Scene classification using multi-scale deeply described visual words. Int. J. Remote. Sens. 2016, 37, 4119–4131. [Google Scholar] [CrossRef]
- Liu, Y.; Huang, C. Scene Classification via Triplet Networks. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2018, 11, 220–237. [Google Scholar] [CrossRef]
- Zhang, F.; Du, B.; Zhang, L. Scene Classification via a Gradient Boosting Random Convolutional Network Framework. IEEE Trans. Geosci. Remote Sens. 2016, 54, 1793–1802. [Google Scholar] [CrossRef]
- Zhang, S.; Wu, R.; Xu, K.; Wang, J.; Sun, W. R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery. Remote. Sens. 2019, 11, 631. [Google Scholar] [CrossRef] [Green Version]
- Zhu, Q.; Zhong, Y.; Zhang, L.; Li, D. Adaptive Deep Sparse Semantic Modeling Framework for High Spatial Resolution Image Scene Classification. IEEE Trans. Geosci. Remote Sens. 2018, 56, 1–16. [Google Scholar] [CrossRef]
- Cheng, G.; Yang, C.; Yao, X.; Guo, L.; Han, J. When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs. IEEE Trans. Geosci. Remote Sens. 2018, 56, 2811–2821. [Google Scholar] [CrossRef]
- Chen, H.; Shi, Z. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection. Remote. Sens. 2020, 12, 1662. [Google Scholar] [CrossRef]
- Li, H.; Cui, Z.; Zhu, Z.; Chen, L.; Zhu, J.; Huang, H.; Tao, C. RS-MetaNet: Deep Metametric Learning for Few-Shot Remote Sensing Scene Classification. IEEE Trans. Geosci. Remote Sens. 2020, 1–12. [Google Scholar] [CrossRef]
- Alajaji, D.; Alhichri, H.S.; Ammour, N.; Alajlan, N. Few-Shot Learning for Remote Sensing Scene Classification. In Proceedings of the 2020 Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS), Tunis, Tunisia, 9–11 March 2020; pp. 81–84. [Google Scholar]
- Zoph, B.; Le, Q.V. Neural Architecture Search with Reinforcement Learning. arXiv 2016, arXiv:1611.01578. [Google Scholar]
- Real, E.; Aggarwal, A.; Huang, Y.; Le, Q.V. Regularized Evolution for Image Classifier Architecture Search. In Proceedings of the Association for the Advancement of Artificial Intelligence, Honolulu, HI, USA, 27 January–1 February 2019; pp. 4780–4789. [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. Available online: http://proceedings.mlr.press/v80/pham18a.html (accessed on 30 July 2021).
- Liu, H.; Simonyan, K.; Yang, Y. DARTS: Differentiable Architecture Search. arXiv 2018, arXiv:1806.09055. [Google Scholar]
- Liang, H.; Zhang, S.; Sun, J.; He, X.; Huang, W.; Zhuang, K.; Li, Z. DARTS+: Improved Differentiable Architecture Search with Early Stopping. arXiv 2019, arXiv:1909.06035. [Google Scholar]
- Peng, C.; Li, Y.; Jiao, L.; Shang, R. Efficient Convolutional Neural Architecture Search for Remote Sensing Image Scene Classification. IEEE Trans. Geosci. Remote. Sens. 2021, 59, 6092–6105. [Google Scholar] [CrossRef]
- Jing, W.; Ren, Q.; Zhou, J.; Song, H. AutoRSISC: Automatic design of neural architecture for remote sensing image scene classification. Pattern Recognit. Lett. 2020, 140, 186–192. [Google Scholar] [CrossRef]
- Xu, Y.; Xie, L.; Zhang, X.; Chen, X.; Qi, G.J.; Tian, Q.; Xiong, H. PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search. arXiv 2019, arXiv:1907.05737. [Google Scholar]
- Baker, B.; Gupta, O.; Naik, N.; Raskar, R. Designing Neural Network Architectures using Reinforcement Learning. arXiv 2016, arXiv:1611.02167. [Google Scholar]
- Brock, A.; Lim, T.; Ritchie, J.M.; Weston, N. SMASH: One-Shot Model Architecture Search through HyperNetworks. arXiv 2017, arXiv:1708.05344. [Google Scholar]
- Liu, C.; Zoph, B.; Neumann, M.; Shlens, J.; Hua, W.; Li, L.-J.; Li, F.-F.; Yuille, A.; Huang, J.; Murphy, K. Progressive Neural Architecture Search. 2018. Available online: https://openaccess.thecvf.com/content_ECCV_2018/html/Chenxi_Liu_Progressive_Neural_Architecture_ECCV_2018_paper.html (accessed on 31 July 2021).
- Finn, C.; Abbeel, P.; Levine, S. Model-agnostic meta-learning for fast adaptation of deep networks. arXiv 2017, arXiv:1703.03400. [Google Scholar]
- Luketina, J.; Berglund, M.; Greff, K.; Raiko, T. Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters. In Proceedings of the International Conference on Machine Learning, New York, NY, USA, 19–24 June 2016; pp. 2952–2960. [Google Scholar]
- Metz, L.; Poole, B.; Pfau, D.; Sohl-Dickstein, J. Unrolled Generative Adversarial Networks. arXiv 2016, arXiv:1611.02163. [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] [CrossRef] [Green Version]
- Chu, X.; Zhou, T.; Zhang, B.; Li, J. Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search. In Computer Vision–ECCV 2020; Springer: Berlin/Heidelberg, Germany, 2020; pp. 465–480. [Google Scholar]
- Chu, X.; Zhang, B.; Li, X. Noisy Differentiable Architecture Search. arXiv 2020, arXiv:2005.03566. [Google Scholar]
- Zhuo, L.; Zhang, B.; Chen, C.; Ye, Q.; Liu, J.; Doermann, D. Calibrated Stochastic Gradient Descent for Convolutional Neural Networks. Proc. Conf. AAAI Artif. Intell. 2019, 33, 9348–9355. [Google Scholar] [CrossRef]
- Xia, G.-S.; Hu, J.; Hu, F.; Shi, B.; Bai, X.; Zhong, Y.; Zhang, L.; Lu, X. AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification. IEEE Trans. Geosci. Remote Sens. 2017, 55, 3965–3981. [Google Scholar] [CrossRef] [Green Version]
- Li, H.; Dou, X.; Tao, C.; Hou, Z.; Chen, J.; Peng, J.; Deng, M.; Zhao, L. RSI-CB: A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data. Sensors 2017, arXiv:1705.1045020, 1594. [Google Scholar] [CrossRef] [Green Version]
- Zhou, W.; Newsam, S.; Li, C.; Shao, Z. PatternNet: A benchmark dataset for performance evaluation of remote sensing image retrieval. ISPRS J. Photogramm. Remote Sens. 2018, 145, 197–209. [Google Scholar] [CrossRef] [Green Version]
- Simonyan, K.; Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 2014, arXiv:1409.1556. [Google Scholar]
- Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with convolutions. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015. [Google Scholar]
- Zhang, J.; Zhang, M.; Shi, L.; Yan, W.; Pan, B. A Multi-Scale Approach for Remote Sensing Scene Classification Based on Feature Maps Selection and Region Representation. Remote Sens. 2019, 11, 2504. [Google Scholar] [CrossRef] [Green Version]
- Deep Feature Fusion for VHR Remote Sensing Scene Classification|IEEE Journals & Magazine|IEEE Xplore. Available online: https://ieeexplore.ieee.org/document/7934005 (accessed on 15 December 2021).
Name | Classes | Total Images | Images/Class | Image Size |
---|---|---|---|---|
NWPURESISC45 [25] | 45 | 31,500 | 700 | 256 |
PatternNet [56] | 38 | 30,400 | 800 | 256 |
RSI-CB256 [55] | 35 | 24,747 | ~690 | 256 |
AID [54] | 30 | 10,000 | 220~420 | 600 |
In Search Phase | AID | NWPU | RSI-CB | PatternNet |
---|---|---|---|---|
NWPU | 86.77% | 90.06% | 99.02% | 98.93% |
PatternNet | 92.78% | 94.58% | 98.81% | 99.56% |
Versions | |
---|---|
GPUs | NVIDIA Tasla V100 |
Pytorch | 1.6.0 |
Python | 3.7.7 |
Hyperparameters | |
---|---|
Epoch | 50 |
Initialization Channel | 16 |
Batch Size | 32 |
L1/L2 weighted decline rate | 10.0 |
Sample channels | 0.5 |
Learning rate in Adam | 0.0006 |
Weighted decline rate in Adam | 0.003 |
Learning rate in SGD | Cosine annealing |
SGD’s momentum | 0.9 |
Weighted decline rate in SGD | 0.0003 |
Hyperparameters | |
---|---|
Epoch | 500 |
Initialization Channel | 36 |
Layers | 20 |
Batch size | 128 |
Cutout’s length | 16 |
Cutout’s path dropout | 0.2 |
Cutmix’s bate | 1 |
Cutmix’s threshold value | 1 |
AID | NWPU | RSI-CB | PatternNet | Training Model | |
---|---|---|---|---|---|
VGG-16 [57] | 88.56% | 85.97% | 96.53% | 97.31% | Fully Trained |
GoogleNet [58] | 84.27% | 83.29% | 96.21% | 96.12% | Fully Trained |
ResNet-50 [50] | 86.94% | 86.96% | 97.09% | 96.71% | Fully Trained |
MDFR [59] | 93.37% | 86.89% | - | - | Fully Trained |
DCA [60] | 89.71% | - | - | - | Fully Trained |
VGG-16 [57] | 92.03% | 91.32% | 97.26% | 98.31% | Pretrained |
GoogleNet [58] | 90.31% | 89.42% | 98.14% | 97.56% | Pretrained |
ResNet-50 [50] | 92.14% | 91.63% | 98.12% | 98.23% | Pretrained |
MSCP(AlexNet) [24] | 88.99% | 85.58% | - | - | Pretrained |
Conv5-MSP5-FV [13] | 93.90% | - | - | - | Pretrained |
RS-DARTS (40% training samples) | 90.43% | 93.56% | 99.30% | 99.43% | Fully trained |
RS-DARTS (60% training samples) | 94.14% | 93.68% | 99.42% | 99.52% | Fully trained |
AID | NWPU | RSI-CB | PatternNet | Search Strategy | |
---|---|---|---|---|---|
DARTS [39] | 79.42% | 74.56% | 97.32% | 95.58% | Grandient |
PC-DARTS [43] | 84.46% | 90.27% | 98.46% | 99.10% | Grandient |
Fair DARTS [51] | 89.46% | 91.38% | 99.14% | 98.88% | Grandient |
GPAS [41] | 93.85% | 92.57% | 98.25% | 99.01% | Grandient |
RS-DARTS | 90.43% | 93.56% | 99.30% | 99.43% | Grandient |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 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.; Liu, S.; Zhang, Y.; Chen, W. RS-DARTS: A Convolutional Neural Architecture Search for Remote Sensing Image Scene Classification. Remote Sens. 2022, 14, 141. https://doi.org/10.3390/rs14010141
Zhang Z, Liu S, Zhang Y, Chen W. RS-DARTS: A Convolutional Neural Architecture Search for Remote Sensing Image Scene Classification. Remote Sensing. 2022; 14(1):141. https://doi.org/10.3390/rs14010141
Chicago/Turabian StyleZhang, Zhen, Shanghao Liu, Yang Zhang, and Wenbo Chen. 2022. "RS-DARTS: A Convolutional Neural Architecture Search for Remote Sensing Image Scene Classification" Remote Sensing 14, no. 1: 141. https://doi.org/10.3390/rs14010141
APA StyleZhang, Z., Liu, S., Zhang, Y., & Chen, W. (2022). RS-DARTS: A Convolutional Neural Architecture Search for Remote Sensing Image Scene Classification. Remote Sensing, 14(1), 141. https://doi.org/10.3390/rs14010141