A Few Shot Classification Methods Based on Multiscale Relational Networks
Source abstract
Abstract
Learning information from a single or a few samples is called few-shot learning. This learning method will solve deep learning’s dependence on a large sample. Deep learning achieves few-shot learning through meta-learning: “how to learn by using previous experience”. Therefore, this paper considers how the deep learning method uses meta-learning to learn and generalize from a small sample size in image classification. The main contents are as follows. Practicing learning in a wide range of tasks enables deep learning methods to use previous empirical knowledge. However, this method is subject to the quality of feature extraction and the selection of measurement methods supports set and the target set. Therefore, this paper designs a multi-scale relational network (MSRN) aiming at the above problems. The experimental results show that the simple design of the MSRN can achieve higher performance. Furthermore, it improves the accuracy of the datasets within fewer samples and alleviates the overfitting situation. However, to ensure that uniform measurement applies to all tasks, the few-shot classification based on metric learning must ensure the task set’s homologous distribution.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Domain Adaptation and Few-Shot Learning · Machine Learning and ELM · Machine Learning and Data Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China
Department of Geography and Anthropology, Louisiana State University, Baton Rouge, LA 70803, USA
Funding
Sichuan Science and Technology Program
References (43)
Show source-provided references
1. Matching networks for one shot learning
2. Ni, X., Yin, L., Chen, X., Liu, S., Yang, B., and Zheng, W. (2018, January 10). Semantic representation for visual reasoning. Proceedings of the 2018 International Joint Conference on Metallurgical and Materials Engineering (JCMME 2018), Wellington, New Zealand.
3. Kadam, V., Kumar, S., Bongale, A., Wazarkar, S., Kamat, P., and Patil, S. (2021). Enhancing surface fault detection using machine learning for 3D printed products. Appl. Syst. Innov., 4.10.3390/asi4020034 ↗
4. Kumar, S., Kolekar, T., Patil, S., Bongale, A., Kotecha, K., Zaguia, A., and Prakash, C. (2022). A Low-Cost Multi-Sensor Data Acquisition System for Fault Detection in Fused Deposition Modelling. Sensors, 22.10.3390/s22020517 ↗
5. The role of metalearning in study processes10.1111/j.2044-8279.1985.tb02625.x ↗
6. Vanschoren, J. (2019). Meta-learning. Automated Machine Learning, Springer.10.1007/978-3-030-05318-5_2 ↗
7. Data-driven remaining useful life estimation for milling process: Sensors, algorithms, datasets, and future directions10.1109/ACCESS.2021.3101284 ↗
8. Finn, C., Abbeel, P., and Levine, S. (2017, January 6–11). Model-agnostic meta-learning for fast adaptation of deep networks. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia.
9. Zintgraf, L., Shiarli, K., Kurin, V., Hofmann, K., and Whiteson, S. (2019, January 9–15). Fast context adaptation via meta-learning. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA.
10. Wang, Y.-X., Ramanan, D., and Hebert, M. (2019, January 27–28). Meta-learning to detect rare objects. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Korea.10.1109/ICCV.2019.01002 ↗
11. Brazdil, P., Carrier, C.G., Soares, C., and Vilalta, R. (2008). Metalearning: Applications to Data Mining, Springer Science & Business Media.10.1007/978-3-540-73263-1 ↗
12. Li, F.-F. (2013, January 13–16). A Bayesian approach to unsupervised one-shot learning of object categories. Proceedings of the Ninth IEEE International Conference on Computer Vision, Washington, DC, USA.
13. One-shot learning of object categories10.1109/TPAMI.2006.79 ↗
14. Kemp, C., and Maas, A.L. (August, January 29). One-Shot Learning with Bayesian Networks. Proceedings of the 31st Annual Meeting of the Cognitive Science Society, Amsterdam, The Netherlands.
15. Lake, B., Salakhutdinov, R., Gross, J., and Tenenbaum, J. (2010, January 11–14). One shot learning of simple visual concepts. Proceedings of the 32nd Annual Meeting of the Cognitive Science Society, Portland, OR, USA.
16. Ding, Y., Tian, X., Yin, L., Chen, X., Liu, S., Yang, B., and Zheng, W. (2015, January 7–13). Multi-scale Relation Network for Few-Shot Learning Based on Meta-learning. Proceedings of the 2015 IEEE International Conference on Computer Vision Systems, Santiago, Chile.
17. Lake, B.M., Salakhutdinov, R.R., and Tenenbaum, J. (2013, January 5–10). One-shot learning by inverting a compositional causal process. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA.
18. Human-level concept learning through probabilistic program induction10.1126/science.aab3050 ↗
19. A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs10.1126/science.aag2612 ↗
20. Building machines that learn and think like people10.1017/S0140525X16001837 ↗
21. Hochreiter, S., Younger, A.S., and Conwell, P.R. (2001, January 21–25). Learning to learn using gradient descent. Proceedings of the 2001 International Conference on Artificial Neural Networks, Vienna, Austria.10.1007/3-540-44668-0_13 ↗
22. Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement10.1023/A:1007383707642 ↗
23. Maclaurin, D., Duvenaud, D., and Adams, R. (2020, January 19–23). Gradient-based hyperparameter optimization through reversible learning. Proceedings of the 37th International Conference on Machine Learning, Siena, Italy.
24. Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., and Lillicrap, T. (2016, January 19–24). Meta-learning with memory-augmented neural networks. Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA.
25. Meta networks
26. Koch, G., Zemel, R., and Salakhutdinov, R. (2015, January 6–11). Siamese neural networks for one-shot image recognition. Proceedings of the 32nd ICML Deep Learning Workshop, Lille, France.
27. Shyam, P., Gupta, S., and Dukkipati, A. (2017, January 6–11). Attentive recurrent comparators. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia.
28. Learning to control fast-weight memories: An alternative to dynamic recurrent networks10.1162/neco.1992.4.1.131 ↗
29. Ravi, S., and Larochelle, H. (2016, January 2–4). Optimization as a model for few-shot learning. Proceedings of the ICLR 2016, San Juan, PR, USA.
30. Comparative Analysis on Classical Meta-Metric Models for Few-Shot Learning10.1109/ACCESS.2020.3008684 ↗
31. Denevi, G., Ciliberto, C., Grazzi, R., and Pontil, M. (2019, January 9–15). Learning-to-Learn Stochastic Gradient Descent with Biased Regularization. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA.
32. Domain-specific meta-embedding with latent semantic structures10.1016/j.ins.2020.10.030 ↗
33. Fielding, B., Lawrence, T., and Zhang, L. (2019, January 13). Evolving and ensembling deep CNN architectures for image classification. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.10.1109/IJCNN.2019.8852369 ↗
34. Automatically designing CNN architectures using the genetic algorithm for image classification10.1109/TCYB.2020.2983860 ↗
35. Guo, Q., Qian, Y., Liang, X., Chen, J., and Cheng, H. (2022). Multi-granulation Multi-scale Relation Network for Abstract Reasoning. Int. J. Mach. Learn. Cybern., 1–12.10.1007/s13042-021-01484-5 ↗
36. Multi-scale relation reasoning for multi-modal Visual Question Answering10.1016/j.image.2021.116319 ↗
37. Multi-scale deep relational reasoning for facial kinship verification10.1016/j.patcog.2020.107541 ↗
38. Jmour, N., Zayen, S., and Abdelkrim, A. (2018, January 22–25). Convolutional neural networks for image classification. Proceedings of the 2018 International Conference on Advanced Systems and Electric Technologies (IC_ASET), Hammamet, Tunisia.10.1109/ASET.2018.8379889 ↗
39. Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., and Hospedales, T.M. (2018, January 18–23). Learning to compare: Relation network for few-shot learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00131 ↗
40. Chen, Q., Zhu, X., Ling, Z., Wei, S., Jiang, H., and Inkpen, D. (2016). Enhanced LSTM for natural language inference. arXiv.10.18653/v1/P17-1152 ↗
41. Graves, A., Jaitly, N., and Mohamed, A.-R. (2013, January 8–12). Hybrid speech recognition with deep bidirectional LSTM. Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic.10.1109/ASRU.2013.6707742 ↗
42. Learning representations by back-propagating errors10.1038/323533a0 ↗
43. Kingma, D.P., and Ba, J.L. (2015, January 7–9). Adam: A method for stochastic gradient descent. Proceedings of the 3rd ICLR: International Conference on Learning Representations, San Diego, CA, USA.