Cited By
View all- Li JWang WLiu XLiao L(2021)Analysis of the nonperfused volume ratio of adenomyosis from MRI images based on fewshot learningPhysics in Medicine & Biology10.1088/1361-6560/abd66b66:4(045019)Online publication date: 8-Feb-2021
Graph attention propagation for few-shot learning
Article No.: 103, Pages 1 - 4
Abstract
Few-shot learning, which learns novel concept from very few samples given some base categories that have sufficient training samples, is a significant yet practical task since plenty of real-world categories have merely very limited samples. The main challenge is how to mine the correlations between the base and novel categories, and transfer information of based categories to help learn novel concepts. To address this work, we propose a graph attention propagation (GAP) model that introduces a graph attention mechanism to mine correlations among categories and propagate information through each other. In this way, the model can adaptively transfer knowledge of the base categories to help learn those novel categories. We conduct experiments on the ImageNet dataset and demonstrate that the GAP model show superior performance for few-shot learning.
References
[1]
Tianshui Chen, Liang Lin, Riquan Chen, Yang Wu, and Xiaonan Luo. 2018. Knowledge-embedded representation learning for fine-grained image recognition. arXiv preprint arXiv:1807.00505 (2018).
[2]
Tianshui Chen, Zhouxia Wang, Guanbin Li, and Liang Lin. 2018. Recurrent attentional reinforcement learning for multi-label image recognition. In Thirty-Second AAAI Conference on Artificial Intelligence.
[3]
Junsuk Choe, Song Park, Kyungmin Kim, Joo Hyun Park, Dongseob Kim, and Hyunjung Shim. 2017. Face generation for low-shot learning using generative adversarial networks. In Computer Vision Workshop (ICCVW), 2017 IEEE International Conference on. IEEE, 1940--1948.
[4]
Victor Garcia and Joan Bruna. 2017. Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043 (2017).
[5]
Spyros Gidaris and Nikos Komodakis. 2018. Dynamic Few-Shot Visual Learning without Forgetting. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4367--4375.
[6]
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680.
[7]
Bharath Hariharan and Ross Girshick. 2017. Low-Shot Visual Recognition by Shrinking and Hallucinating Features. In 2017 IEEE International Conference on Computer Vision (ICCV). IEEE, 3037--3046.
[8]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.
[9]
Gregory Koch, Richard Zemel, and Ruslan Salakhutdinov. 2015. Siamese neural networks for one-shot image recognition. In ICML Deep Learning Workshop, Vol. 2.
[10]
Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.
[11]
Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). 1532--1543.
[12]
Hang Qi, Matthew Brown, and David G Lowe. 2018. Low-Shot Learning With Imprinted Weights. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5822--5830.
[13]
Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).
[14]
Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. In Advances in Neural Information Processing Systems. 4077--4087.
[15]
Oriol Vinyals, Charles Blundell, Tim Lillicrap, Daan Wierstra, et al. 2016. Matching networks for one shot learning. In Advances in Neural Information Processing Systems. 3630--3638.
[16]
Yu-Xiong Wang, Ross Girshick, Martial Hebert, and Bharath Hariharan. 2018. Low-Shot Learning from Imaginary Data. In IEEE Conference on Computer Vision and Pattern Recognition.
[17]
Yu-Xiong Wang and Martial Hebert. 2016. Learning to learn: Model regression networks for easy small sample learning. In European Conference on Computer Vision. Springer, 616--634.
[18]
Zhouxia Wang, Tianshui Chen, Guanbin Li, Ruijia Xu, and Liang Lin. 2017. Multi-label image recognition by recurrently discovering attentional regions. In Proceedings of the IEEE International Conference on Computer Vision. 464--472.
Index Terms
- Graph attention propagation for few-shot learning
Recommendations
Robust Graph Meta-Learning for Weakly Supervised Few-Shot Node Classification
Graph machine learning (Graph ML) models typically require abundant labeled instances to provide sufficient supervision signals, which is commonly infeasible in real-world scenarios since labeled data for newly emerged concepts (e.g., new categorizations ...
Multi-attention mutual information distributed framework for few-shot learning
AbstractThe purpose of few-shot learning is to learn a classifier, even if only a limited number of samples are used, a good generalization effect can be achieved. Recently, many methods based on meta-learning learn a large number of multi-...
Highlights- Mutual learning module based on the multi-attention mechanism.
- Combine few-shot ...
Prior-knowledge and attention based meta-learning for few-shot learning
AbstractRecently, meta-learning has been shown to be a promising way to solve few-shot learning. In this paper, inspired by the human cognition process, which utilizes both prior-knowledge and visual attention when learning new knowledge, we ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
May 2019
963 pages
ISBN:9781450371582
DOI:10.1145/3321408
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 17 May 2019
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
ACM TURC 2019
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 233Total Downloads
- Downloads (Last 12 months)8
- Downloads (Last 6 weeks)0
Reflects downloads up to 24 Sep 2024
Other Metrics
Citations
Cited By
View all- Li JWang WLiu XLiao L(2021)Analysis of the nonperfused volume ratio of adenomyosis from MRI images based on fewshot learningPhysics in Medicine & Biology10.1088/1361-6560/abd66b66:4(045019)Online publication date: 8-Feb-2021
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in