Background-Filtering Feature-Enhanced Graph Neural Networks for Few-Shot Learning
Source abstract
Abstract
The fundamental idea behind few-shot learning is to employ sparse labeled data to effectively handle novel tasks, whereas most existing mainstream approaches mostly rely on prior experience gained from previous situations. Nonetheless, effective knowledge transfer is sometimes hampered by constraints on new samples and barriers between classes. To address these issues, this research presents a novel background-filtering feature-enhanced graph network (BFFE-GNN) that attempts to generate relationships between graphs in order to explicitly describe and transmit inter-class relationships. To specifically address the issue of inadequate information utilization brought on by sample background interference, which is frequent in classification tasks, we employ a novel background-filtering feature-enhanced graph network. Effective data information extraction from complicated datasets is challenging due to the original module’s relatively simple network structure during the feature extraction stage and the interference of the image background. The background-filtering module was specifically introduced, which enhances spatial attention. This not only improves the quality of feature extraction but also effectively lessens the influence of picture background on classification results. In addition, we have improved the background-filtering-based feature gap calculation by implementing a feature-enhanced module. To demonstrate the adaptability of the BFFE-GNN model, we not only ran experiments on two publicly available datasets, MiniImagenet and TiredImagenet, but we also created our own Tool dataset. The method’s exceptional performance and universal applicability in the field of few-shot picture classification are clearly demonstrated by the experimental findings, which indicate that it greatly outperforms the majority of existing similar methods. This discovery establishes a strong basis for further research in the field of few-shot learning in addition to offering fresh insights into the subject.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Domain Adaptation and Few-Shot Learning · Machine Learning and ELM · Advanced Graph Neural Networks
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer and Information Engineering, Harbin University of Commerce, Harbin 150028, China
Institute of System Engineering, Harbin University of Commerce, Harbin 150028, China
Funding
The Nature Science Foundation of Heilongjiang Province
References (41)
Show source-provided references
1. Enhancing sketch based image retrieval by CNN semantic re-ranking10.1109/TCYB.2019.2894498 ↗
2. Adaptive and robust partition learning for person retrieval with policy gradient10.1109/TMM.2020.3023272 ↗
3. Learning refined attribute-aligned network with attribute selection for person re-identification10.1016/j.neucom.2020.03.057 ↗
4. Unsupervised descriptor selection based meta-learning networks for few-shot classification10.1016/j.patcog.2021.108304 ↗
5. Gidaris, S., and Komodakis, N. (2018, January 18–23). Dynamic few-shot visual learning without forgetting. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00459 ↗
6. Hariharan, B., and Girshick, R. (2017, January 22–29). Low-shot visual recognition by shrinking and hallucinating features. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.328 ↗
7. A perspective view and survey of meta-learning10.1023/A:1019956318069 ↗
8. A survey of deep meta-learning10.1007/s10462-021-10004-4 ↗
9. Financial time series forecasting with multi-modality graph neural network10.1016/j.patcog.2021.108218 ↗
10. Garcia, V., and Bruna, J. (May, January 30). Few-shot learning with graph neural networks. Proceedings of the 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada.
11. Liu, Y., Lee, J., Park, M., Kim, S., Yang, E., Hwang, S.J., and Yang, Y. (2019, January 6–9). Learning to propagate labels: Transductive propagation network for few-shot learning. Proceedings of the 7th International Conference on Learning Representations, (ICLR Poster), New Orleans, LA, USA.
12. Kim, J., Kim, T., Kim, S., and Yoo, C.D. (2019, January 15–20). Edge-labeling graph neural network for few-shot learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00010 ↗
13. Luo, Y., Huang, Z., Zhang, Z., Wang, Z., Baktashmotlagh, M., and Yang, Y. (2020, January 7–12). Learning from the past: Continual meta-learning with Bayesian graph neural networks. Proceedings of the 34th AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i04.5942 ↗
14. Zhou, B., Zhao, J., Yan, C., Zhang, X., and Gu, J. (2023). Global and local knowledge distillation method for few-shot classification of electrical equipment. Appl. Sci., 13.10.20944/preprints202305.0102.v1 ↗
15. Survey of few-shot object detection
16. Hutter, F., Kotthoff, L., and Vanschoren, J. (2019). Automated Machine Learning: Methods, Systems, Challenges, Springer Publishing Company, Incorporated.10.1007/978-3-030-05318-5 ↗
17. Geometric deep learning: Going beyond Euclidean data10.1109/MSP.2017.2693418 ↗
18. Xu, Y., and Wang, Y. (2023). Fused Node-Level Residual Structure Edge Graph Neural Network for Few-Shot Image Classification. Appl. Sci., 13.10.3390/app131910996 ↗
19. Kipf, T.N., and Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. arXiv.
20. Zhang, M., and Chen, Y. (2018). Link Prediction Based on Graph Neural Networks. Advances in Neural Information Processing Systems (NeurIPS), Curran Associates, Inc.
21. Xu, K., Hu, W., Leskovec, J., and Jegelka, S. (2019, January 6–9). How Powerful are Graph Neural Networks?. Proceedings of the International Conference on Learning Representations (ICLR), New Orleans, LA, USA.
22. Koch, G., Zemel, R., and Salakhutdinov, R. (2015, January 6–11). Siamese neural networks for one-shot image recognition. Proceedings of the ICML Deep Learning Workshop, Lille, France.
23. Snell, J., Swersky, K., and Zemel, R. (2017). Prototypical networks for few-shot learning. Advances in Neural Information Processing Systems, Curran Associates, Inc.
24. 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 ↗
25. Cai, Q., Pan, Y., Yao, T., Yan, C., and Mei, T. (2018, January 18–23). Memory matching networks for one-shot image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00429 ↗
26. Zhang, R., Che, T., Ghahramani, Z., Bengio, Y., and Song, Y. (2018). Metagan: An adversarial approach to few-shot learning. Advances in Neural Information Processing Systems, Curran Associates, Inc.
27. Correlation clustering10.1023/B:MACH.0000033116.57574.95 ↗
28. Finley, T., and Joachims, T. (2005, January 7–11). Supervised clustering with support vector machines. Proceedings of the 22nd International Conference on Machine Learning (ICML 2005), Bonn, Germany.10.1145/1102351.1102379 ↗
29. Taskar, B. (2004). Learning Structured Prediction Models: A Large Margin Approach. [Ph.D. Thesis, Stanford University].10.1145/1102351.1102464 ↗
30. Kim, S., Nowozin, S., Kohli, P., and Yoo, C.D. (2011). Higher-order correlation clustering for image segmentation. Advances in Neural Information Processing Systems, Curran Associates, Inc.
31. Gong, L., and Cheng, Q. (2018). Adaptive edge features guided graph attention networks. arXiv.
32. Johnson, D.D. (2016, January 2–4). Learning graphical state transitions. Proceedings of the 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico.
33. Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., and Wierstra, D. (2016). Matching networks for one shot learning. Advances in Neural Information Processing Systems, Curran Associates, Inc.
34. Imagenet large scale visual recognition challenge10.1007/s11263-015-0816-y ↗
35. Ren, M., Triantafillou, E., Ravi, S., Snell, J., Swersky, K., Tenenbaum, J.B., Larochelle, H., and Zemel, R.S. (2018). Meta-learning for semi-supervised fewshot classification. arXiv.
36. Gidaris, S., and Komodakis, N. (2019). Generating classification weights with GNN denoising autoencoders for few-shot learning. arXiv.10.1109/CVPR.2019.00011 ↗
37. Mishra, N., Rohaninejad, M., Chen, X., and Abbeel, P. (2019, January 6–9). A simple neural attentive meta-learner. Proceedings of the 7th International Conference on Learning Representations, (ICLR Poster), New Orleans, LA, USA.
38. Oreshkin, B.N., López, P.R., and Lacoste, A. (2018). TADAM: Task dependent adaptive metric for improved few-shot learning. Advances in Neural Information Processing Systems, Curran Associates, Inc.
39. Ravichandran, A., Bhotika, R., and Soatto, S. (November, January 27). Few-shot learning with embedded class models and shot-free meta training. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.
40. Li, Z., Zhou, F., Chen, F., and Li, H. (2017). Meta-sgd: Learning to learn quickly for few-shot learning. arXiv.
41. Rusu, A.A., Rao, D., Sygnowski, J., Vinyals, O., Pascanu, R., Osindero, S., and Hadsell, R. (2018). Meta-learning with latent embedding optimization. arXiv.