publication . Preprint . 2018

Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions

Ye, Han-Jia; Hu, Hexiang; Zhan, De-Chuan; Sha, Fei;
Open Access English
  • Published: 10 Dec 2018
Abstract
Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels. This style of transfer learning is task-agnostic: the embedding function is not learned optimally discriminative with respect to the unseen classes, where discerning among them leads to the target task. In this paper, we propose a novel approach to adapt the instance embeddings to the target classification task with a set-to-set function, yielding embeddings that are task-specific and are discriminative. ...
Subjects
free text keywords: Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition
Funded by
NSF| RI: Medium: Collaborative Research: Learning to Summarize User-Generated Video
Project
  • Funder: National Science Foundation (NSF)
  • Project Code: 1513966
,
NSF| NRI-Small: Spacial Primitives for Enabling Situated Human-Robot Interaction
Project
  • Funder: National Science Foundation (NSF)
  • Project Code: 1208500
  • Funding stream: Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems
,
NSF| RI: Medium: Collaborative Research: Semantically Discriminative: Guiding Mid-Level Representations for Visual Object Recognition with External Knowledge
Project
  • Funder: National Science Foundation (NSF)
  • Project Code: 1065243
  • Funding stream: Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems
,
NSF| RI: Medium: Collaborative Research: Learning to Summarize User-Generated Video
Project
  • Funder: National Science Foundation (NSF)
  • Project Code: 1632803
,
NSF| Collaborative Research: Socially Assistive Robots
Project
  • Funder: National Science Foundation (NSF)
  • Project Code: 1139148
  • Funding stream: Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems
Download from
50 references, page 1 of 4

[1] Z. Akata, F. Perronnin, Z. Harchaoui, and C. Schmid. Labelembedding for attribute-based classification. In 2013 IEEE Conference on Computer Vision and Pattern Recognition, pages 819-826. IEEE, 2013. [OpenAIRE]

[2] M. Andrychowicz, M. Denil, S. G. Colmenarejo, M. W. Hoffman, D. Pfau, T. Schaul, and N. de Freitas. Learning to learn by gradient descent by gradient descent. In Advances in Neural Information Processing Systems 29, pages 3981- 3989. Curran Associates, Inc., 2016. [OpenAIRE]

[3] Anonymous. A closer look at few-shot classification. In Submitted to International Conference on Learning Representations, 2019. under review.

[4] L. J. Ba, R. Kiros, and G. E. Hinton. Layer normalization. CoRR, abs/1607.06450, 2016.

[5] S. Changpinyo, W.-L. Chao, B. Gong, and F. Sha. Synthesized classifiers for zero-shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5327-5336, 2016. [OpenAIRE]

[6] S. Changpinyo, W.-L. Chao, and F. Sha. Predicting visual exemplars of unseen classes for zero-shot learning. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 3496-3505. IEEE, 2017. [OpenAIRE]

[7] W.-L. Chao, S. Changpinyo, B. Gong, and F. Sha. An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In Proceedings of the 14th European Conference on Computer Vision, pages 52-68, Amsterdam, The Netherlands, 2016.

[8] M. Dehghani, S. Gouws, O. Vinyals, J. Uszkoreit, and L. Kaiser. Universal transformers. CoRR, abs/1807.03819, 2018. [OpenAIRE]

[9] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. FeiFei. Imagenet: A large-scale hierarchical image database. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 248-255. Ieee, 2009.

[10] C. Finn, P. Abbeel, and S. Levine. Model-agnostic metalearning for fast adaptation of deep networks. In Proceedings of the 34th International Conference on Machine Learning, pages 1126-1135, Sydney, Australia, 2017.

[11] V. Garcia and J. Bruna. Few-shot learning with graph neural networks. CoRR, abs/1711.04043, 2017.

[12] S. Gidaris and N. Komodakis. Dynamic few-shot visual learning without forgetting. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4367-4375, Salt Lake City, UT., 2018. [OpenAIRE]

[13] B. Hariharan and R. B. Girshick. Low-shot visual recognition by shrinking and hallucinating features. In IEEE International Conference on Computer Vision, pages 3037-3046, Venice, Italy, 2017.

[14] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770-778, 2016.

[15] S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning, pages 448-456, Lille, France, 2015.

50 references, page 1 of 4
Abstract
Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels. This style of transfer learning is task-agnostic: the embedding function is not learned optimally discriminative with respect to the unseen classes, where discerning among them leads to the target task. In this paper, we propose a novel approach to adapt the instance embeddings to the target classification task with a set-to-set function, yielding embeddings that are task-specific and are discriminative. ...
Subjects
free text keywords: Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition
Funded by
NSF| RI: Medium: Collaborative Research: Learning to Summarize User-Generated Video
Project
  • Funder: National Science Foundation (NSF)
  • Project Code: 1513966
,
NSF| NRI-Small: Spacial Primitives for Enabling Situated Human-Robot Interaction
Project
  • Funder: National Science Foundation (NSF)
  • Project Code: 1208500
  • Funding stream: Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems
,
NSF| RI: Medium: Collaborative Research: Semantically Discriminative: Guiding Mid-Level Representations for Visual Object Recognition with External Knowledge
Project
  • Funder: National Science Foundation (NSF)
  • Project Code: 1065243
  • Funding stream: Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems
,
NSF| RI: Medium: Collaborative Research: Learning to Summarize User-Generated Video
Project
  • Funder: National Science Foundation (NSF)
  • Project Code: 1632803
,
NSF| Collaborative Research: Socially Assistive Robots
Project
  • Funder: National Science Foundation (NSF)
  • Project Code: 1139148
  • Funding stream: Directorate for Computer & Information Science & Engineering | Division of Information and Intelligent Systems
Download from
50 references, page 1 of 4

[1] Z. Akata, F. Perronnin, Z. Harchaoui, and C. Schmid. Labelembedding for attribute-based classification. In 2013 IEEE Conference on Computer Vision and Pattern Recognition, pages 819-826. IEEE, 2013. [OpenAIRE]

[2] M. Andrychowicz, M. Denil, S. G. Colmenarejo, M. W. Hoffman, D. Pfau, T. Schaul, and N. de Freitas. Learning to learn by gradient descent by gradient descent. In Advances in Neural Information Processing Systems 29, pages 3981- 3989. Curran Associates, Inc., 2016. [OpenAIRE]

[3] Anonymous. A closer look at few-shot classification. In Submitted to International Conference on Learning Representations, 2019. under review.

[4] L. J. Ba, R. Kiros, and G. E. Hinton. Layer normalization. CoRR, abs/1607.06450, 2016.

[5] S. Changpinyo, W.-L. Chao, B. Gong, and F. Sha. Synthesized classifiers for zero-shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5327-5336, 2016. [OpenAIRE]

[6] S. Changpinyo, W.-L. Chao, and F. Sha. Predicting visual exemplars of unseen classes for zero-shot learning. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 3496-3505. IEEE, 2017. [OpenAIRE]

[7] W.-L. Chao, S. Changpinyo, B. Gong, and F. Sha. An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In Proceedings of the 14th European Conference on Computer Vision, pages 52-68, Amsterdam, The Netherlands, 2016.

[8] M. Dehghani, S. Gouws, O. Vinyals, J. Uszkoreit, and L. Kaiser. Universal transformers. CoRR, abs/1807.03819, 2018. [OpenAIRE]

[9] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. FeiFei. Imagenet: A large-scale hierarchical image database. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 248-255. Ieee, 2009.

[10] C. Finn, P. Abbeel, and S. Levine. Model-agnostic metalearning for fast adaptation of deep networks. In Proceedings of the 34th International Conference on Machine Learning, pages 1126-1135, Sydney, Australia, 2017.

[11] V. Garcia and J. Bruna. Few-shot learning with graph neural networks. CoRR, abs/1711.04043, 2017.

[12] S. Gidaris and N. Komodakis. Dynamic few-shot visual learning without forgetting. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4367-4375, Salt Lake City, UT., 2018. [OpenAIRE]

[13] B. Hariharan and R. B. Girshick. Low-shot visual recognition by shrinking and hallucinating features. In IEEE International Conference on Computer Vision, pages 3037-3046, Venice, Italy, 2017.

[14] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770-778, 2016.

[15] S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning, pages 448-456, Lille, France, 2015.

50 references, page 1 of 4
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue