SAR Target Incremental Recognition Based on Hybrid Loss Function and Class-Bias Correction
Source abstract
Abstract
The Synthetic Aperture Radar (SAR) target recognition model usually needs to be retrained with all the samples when there are new-coming samples of new targets. Incremental learning emerges to continuously obtain new knowledge from new data while preserving most previously learned knowledge, saving both time and storage. There are still three problems in the existing incremental learning methods: (1) the recognition performance of old target classes degrades significantly during the incremental process; (2) the target classes are easily confused when similar target classes increase; (3) the model is inclined to new target classes due to class imbalance. Regarding the three problems, firstly, the old sample preservation and knowledge distillation were introduced to preserve both old representative knowledge and knowledge structure. Secondly, a class separation loss function was designed to reduce the intra-class distance and increase the inter-class distance, effectively avoiding the confusion between old and new classes. Thirdly, a bias correction layer and a linear model was designed, which enabled the model to treat the old and new target classes more fairly and eliminate the bias. The experimental results on the MSTAR dataset verified the superior performance compared with the other incremental learning methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Domain Adaptation and Few-Shot Learning · Advanced SAR Imaging Techniques · Machine Learning and ELM
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
Interdisciplinary Research Center for Artificial Intelligence, Beijing University of Chemical Technology, Beijing 100029, China
Funding
National Natural Science Foundation of China · Fundamental Research Funds for the Central Universities
References (39)
Show source-provided references
1. New aspects of global climate-dynamics research and remote sensing10.1080/01431161.2010.517807 ↗
2. SAR Target Small Sample Recognition Based on CNN Cascaded Features and AdaBoost Rotation Forest10.1109/LGRS.2019.2939156 ↗
3. A lossless lightweight CNN design for SAR target recognition10.1080/2150704X.2020.1730472 ↗
4. Target Classification Using the Deep Convolutional Networks for SAR Images10.1109/TGRS.2016.2551720 ↗
5. Wang, Z., Wang, C., Pei, J., Huang, Y., Zhang, Y., Yang, H., and Xing, Z. (2021, January 11–16). Multi-View SAR Automatic Target Recognition Based on Deformable Convolutional Network. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium.10.1109/IGARSS47720.2021.9553308 ↗
6. Class boundary exemplar selection based incremental learning for automatic target recognition10.1109/TGRS.2020.2970076 ↗
7. Lu, X., Sun, X., Diao, W., Feng, Y., Wang, P., and Fu, K. (2021). LIL: Lightweight Incremental Learning Approach Through Feature Transfer for Remote Sensing Image Scene Classification. IEEE Trans. Geosci. Remote Sens., 1–20.10.1109/TGRS.2021.3102629 ↗
8. Rebuffi, S.A., Kolesnikov, A., Sperl, G., and Lampert, C.H. (2017, January 21–26). iCaRL: Incremental classifier and representation Learning. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.587 ↗
9. Overcoming catastrophic forgetting in neural networks10.1073/pnas.1611835114 ↗
10. Peng, J., Tang, B., Jiang, H., Li, Z., Lei, Y., Lin, T., and Li, H. (2021). Overcoming Long-Term Catastrophic Forgetting Through Adversarial Neural Pruning and Synaptic Consolidation. IEEE Trans. Neural Netw. Learn. Syst., 1–14.
11. Lee, J.J., Il Lee, S., and Kim, H. (2021, January 6–9). Continual Learning for Instance Segmentation to Mitigate Catastrophic Forgetting. Proceedings of the 2021 18th International SoC Design Conference (ISOCC), Jeju Island, Korea.10.1109/ISOCC53507.2021.9613885 ↗
12. Castro, F.M., Marín-Jiménez, M.J., Guil, N., Schmid, C., and Alahari, K. (2018, January 8–14). End-to-end incremental learning. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01258-8_15 ↗
13. Fernando, C., Banarse, D., Blundell, C., Zwols, Y., Ha, D., Rusu, A.A., Pritzel, A., and Wierstra, D. (2017). Pathnet: Evolution channels gradient descent in super neural networks. arXiv.
14. Golkar, S., Kagan, M., and Cho, K. (2019). Continual learning via neural pruning. arXiv.
15. Learning without forgetting10.1109/TPAMI.2017.2773081 ↗
16. Lopez-Paz, D., and Ranzato, M. (2017, January 4–9). Gradient episodic memory for continual learning. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA.
17. Shin, H., Lee, J.K., Kim, J., and Kim, J. (2017). Continual learning with deep generative replay. arXiv.
18. Kemker, R., and Kanan, C. (May, January 30). FearNet: Brain-inspired model for incremental learning. Proceedings of the 6th International Conference on Learning Representations, Vancouver, BC, Canada.
19. Distilling the knowledge in a neural network
20. Dastidar, S.G., Dutta, K., Das, N., Kundu, M., and Nasipuri, M. (2021, January 7–8). Exploring knowledge distillation of a deep neural network for multi-script identification. Proceedings of the International Conference on Computational Intelligence in Communications and Business Analytics, Santiniketan, India.10.1007/978-3-030-75529-4_12 ↗
21. Dong, Q., Gong, S., and Zhu, X. (2017, January 27–29). Class rectification hard mining for imbalanced deep learning. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.205 ↗
22. Aljundi, R., Chakravarty, P., and Tuytelaars, T. (2017, January 21–26). Expert gate: Lifelong learning with a network of experts. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.753 ↗
23. Online continual learning in image classification: An empirical survey10.1016/j.neucom.2021.10.021 ↗
24. CILEA-NET: Curriculum-Based Incremental Learning Framework for Remote Sensing Image Classification10.1109/JSTARS.2021.3084408 ↗
25. Park, W., Kim, D., Lu, Y., and Cho, M. (2019, January 15–20). Relational knowledge distillation. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00409 ↗
26. Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., Zhang, Z., and Fu, Y. (2018). Incremental classifier learning with generative adversarial networks. arXiv.
27. Dhar, P., Singh, R.V., Peng, K.C., Wu, Z., and Chellappa, R. (2019, January 15–20). Learning without memorizing. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00528 ↗
28. Hou, S., Pan, X., Loy, C.C., Wang, Z., and Lin, D. (2019, January 15–20). Learning a unified classifier incrementally via rebalancing. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00092 ↗
29. Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., and Fu, Y. (2019, January 15–20). Large scale incremental learning. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00046 ↗
30. Zhou, P., Mai, L., Zhang, J., Xu, N., Wu, Z., and Davis, L.S. (2019). M2kd: Multi-model and multi-level knowledge distillation for incremental learning. arXiv.
31. Belouadah, E., and Popescu, A. (2019, January 27–28). IL2M: Class incremental learning with dual memory. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.10.1109/ICCV.2019.00067 ↗
32. Belouadah, E., and Popescu, A. (2020, January 1–5). ScaIL: Classifier weights scaling for class incremental learning. Proceedings of the 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), Snowmass Village, CO, USA.10.1109/WACV45572.2020.9093562 ↗
33. Liu, Y., Su, Y., Liu, A.A., Schiele, B., and Sun, Q. (2020, January 13–19). Mnemonics training: Multi-class incremental learning without forgetting. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01226 ↗
34. Welling, M. (2009, January 14–18). Herding dynamical weights to learn. Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, QC, Canada.10.1145/1553374.1553517 ↗
35. Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A. (2017, January 4–9). Automatic differentiation in pytorch. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA.
36. Aydin, M.A. (2021, January 9–11). Using Generative Adversarial Networks for Handling Class Imbalance Problem. Proceedings of the 2021 29th Signal Processing and Communications Applications Conference (SIU), Istanbul, Turkey.10.1109/SIU53274.2021.9477939 ↗
37. Zhao, B., Xiao, X., Gan, G., Zhang, B., and Xia, S.T. (2020, January 13–19). Maintaining discrimination and fairness in class incremental learning. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01322 ↗
38. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
39. Liu, X., Masana, M., Herranz, L., Van de Weijer, J., López, A.M., and Bagdanov, A.D. (2018, January 20–24). Rotate your networks: Better weight consolidation and less catastrophic forgetting. Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China.10.1109/ICPR.2018.8545895 ↗