Article

An embarrassingly simple approach to zero-shot learning

Authors:

Bernardino Romera-Paredes,

Philip H. S. TorrAuthors Info & Claims

ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37

Pages 2152 - 2161

Published: 06 July 2015 Publication History

Abstract

Zero-shot learning consists in learning how to recognise new concepts by just having a description of them. Many sophisticated approaches have been proposed to address the challenges this problem comprises. In this paper we describe a zero-shot learning approach that can be implemented in just one line of code, yet it is able to outperform state of the art approaches on standard datasets. The approach is based on a more general framework which models the relationships between features, attributes, and classes as a two linear layers network, where the weights of the top layer are not learned but are given by the environment. We further provide a learning bound on the generalisation error of this kind of approaches, by casting them as domain adaptation methods. In experiments carried out on three standard real datasets, we found that our approach is able to perform significantly better than the state of art on all of them, obtaining a ratio of improvement up to 17%.

References

[1]

Akata, Zeynep, Perronnin, Florent, Harchaoui, Zaid, and Schmid, Cordelia. Label-embedding for attribute-based classification. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pp. 819-826. IEEE, 2013.

[2]

Argyriou, Andreas, Evgeniou, Theodoros, and Pontil, Massimiliano. Convex multi-task feature learning. Machine Learning, 73(3):243-272, 2008.

[3]

Argyriou, Andreas, Micchelli, Charles A, and Pontil, Massimiliano. When is there a representer theorem? vector versus matrix regularizers. The Journal of Machine Learning Research, 10:2507-2529, 2009.

[4]

Ben-David, Shai, Blitzer, John, Crammer, Koby, Pereira, Fernando, et al. Analysis of representations for domain adaptation. Advances in neural information processing systems, 19:137, 2007.

[5]

Blitzer, John, Crammer, Koby, Kulesza, Alex, Pereira, Fernando, and Wortman, Jennifer. Learning bounds for domain adaptation. In Advances in neural information processing systems, pp. 129-136, 2008.

[6]

Bosch, Anna, Zisserman, Andrew, and Munoz, Xavier. Representing shape with a spatial pyramid kernel. In Proceedings of the 6th ACM international conference on Image and video retrieval, pp. 401-408. ACM, 2007.

[7]

Croonenborghs, Tom, Driessens, Kurt, and Bruynooghe, Maurice. Learning relational options for inductive transfer in relational reinforcement learning. In Inductive Logic Programming, pp. 88-97. Springer, 2008.

[8]

Daumé III, Hal. Frustratingly easy domain adaptation. arXiv preprint arXiv:0907.1815, 2009.

[9]

Dietterich, Thomas G. and Bakiri, Ghulum. Solving multiclass learning problems via error-correcting output codes. arXiv preprint cs/9501101, 1995.

[10]

Farhadi, Ali, Endres, Ian, Hoiem, Derek, and Forsyth, David. Describing objects by their attributes. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pp. 1778-1785. IEEE, 2009.

[11]

Ferrari, Vittorio and Zisserman, Andrew. Learning visual attributes. In Advances in Neural Information Processing Systems, pp. 433-440, 2007.

[12]

Frome, Andrea, Corrado, Greg S, Shlens, Jon, Bengio, Samy, Dean, Jeff, Mikolov, Tomas, et al. Devise: A deep visual-semantic embedding model. In Advances in Neural Information Processing Systems, pp. 2121-2129, 2013.

[13]

Fu, Yanwei, Hospedales, Timothy M, Xiang, Tao, and Gong, Shaogang. Learning multimodal latent attributes. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 36(2):303-316, 2014.

[14]

Hariharan, Bharath, Vishwanathan, SVN, and Varma, Manik. Efficient max-margin multi-label classification with applications to zero-shot learning. Machine learning, 88(1-2):127-155, 2012.

[15]

Hwang, Sung Ju, Sha, Fei, and Grauman, Kristen. Sharing features between objects and their attributes. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pp. 1761-1768. IEEE, 2011.

[16]

Jayaraman, Dinesh and Grauman, Kristen. Zero-shot recognition with unreliable attributes. pp. 3464-3472, 2014.

[17]

Jayaraman, Dinesh, Sha, Fei, and Grauman, Kristen. Decorrelating semantic visual attributes by resisting the urge to share. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, pp. 1629-1636. IEEE, 2014.

[18]

Jiang, Jing and Zhai, ChengXiang. Instance weighting for domain adaptation in nlp. In ACL, volume 7, pp. 264- 271, 2007.

[19]

Kifer, Daniel, Ben-David, Shai, and Gehrke, Johannes. Detecting change in data streams. In Proceedings of the Thirtieth international conference on Very large data bases-Volume 30, pp. 180-191. VLDB Endowment, 2004.

[20]

Lampert, Christoph H, Nickisch, Hannes, and Harmeling, Stefan. Learning to detect unseen object classes by between-class attribute transfer. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pp. 951-958. IEEE, 2009.

[21]

Lampert, Christoph H, Nickisch, Hannes, and Harmeling, Stefan. Attribute-based classification for zero-shot visual object categorization. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 36(3):453-465, 2014.

[22]

Lawrence, Neil D and Platt, John C. Learning to learn with the informative vector machine. In Proceedings of the twenty-first international conference on Machine learning, pp. 65. ACM, 2004.

[23]

Liu, Jingen, Kuipers, Benjamin, and Savarese, Silvio. Recognizing human actions by attributes. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pp. 3337-3344. IEEE, 2011.

[24]

Lowe, David G. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2):91-110, 2004.

[25]

Mahajan, Dhruv, Sellamanickam, Sundararajan, and Nair, Vinod. A joint learning framework for attribute models and object descriptions. In Computer Vision (ICCV), 2011 IEEE International Conference on, pp. 1227-1234. IEEE, 2011.

[26]

Palatucci, Mark, Hinton, Geoffrey, Pomerleau, Dean, and Mitchell, Tom M. Zero-Shot Learning with Semantic Output Codes. Neural Information Processing Systems, pp. 1-9, 2009.

[27]

Pan, Sinno Jialin and Yang, Qiang. A survey on transfer learning. Knowledge and Data Engineering, IEEE Transactions on, 22(10):1345-1359, 2010.

[28]

Patterson, Genevieve and Hays, James. Sun attribute database: Discovering, annotating, and recognizing scene attributes. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pp. 2751-2758. IEEE, 2012.

[29]

Raykar, Vikas C, Krishnapuram, Balaji, Bi, Jinbo, Dundar, Murat, and Rao, R Bharat. Bayesian multiple instance learning: automatic feature selection and inductive transfer. In Proceedings of the 25th international conference on Machine learning, pp. 808-815. ACM, 2008.

[30]

Romera-Paredes, Bernardino, Aung, Hane, Bianchi-Berthouze, Nadia, and Pontil, Massimiliano. Multilinear multitask learning. In Proceedings of the 30th International Conference on Machine Learning, pp. 1444-1452, 2013.

[31]

Rückert, Ulrich and Kramer, Stefan. Kernel-based inductive transfer. In Machine Learning and Knowledge Discovery in Databases, pp. 220-233. Springer, 2008.

[32]

Suzuki, Masahiro, Sato, Haruhiko, Oyama, Satoshi, and Kurihara, Masahito. Transfer learning based on the observation probability of each attribute. In Systems, Man and Cybernetics (SMC), 2014 IEEE International Conference on, pp. 3627-3631. IEEE, 2014.

[33]

Wang, Yang and Mori, Greg. A discriminative latent model of object classes and attributes. In Computer Vision-ECCV 2010, pp. 155-168. Springer, 2010.

Cited By

Yan JYin ZXu CDeng CHuang HSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Retrieval across any domains via large-scale pre-trained modelProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694374(55901-55912)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3694374
Astras NVogiatzis D(2024)Prediction of Drug-Drug Interactions with Zero-Shot LearningProceedings of the 13th Hellenic Conference on Artificial Intelligence10.1145/3688671.3688756(1-8)Online publication date: 11-Sep-2024
https://dl.acm.org/doi/10.1145/3688671.3688756
Chen CTang LHuang YHan XYu YOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)CODAProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3666682(12746-12759)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3666682
Show More Cited By

An embarrassingly simple approach to zero-shot learning
1. Computing methodologies

Recommendations

A Survey of Zero-Shot Learning: Settings, Methods, and Applications
Survey Papers and Regular Papers

Most machine-learning methods focus on classifying instances whose classes have already been seen in training. In practice, many applications require classifying instances whose classes have not been seen previously. Zero-shot learning is a powerful and ...
An embarrassingly simple approach to semi-supervised few-shot learning
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing Systems

Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data. Many sophisticated methods have been developed to address the challenges this problem comprises. ...
Transductive Visual-Semantic Embedding for Zero-shot Learning
ICMR '17: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval

Zero-shot learning (ZSL) aims to bridge the knowledge transfer via available semantic representations (e.g., attributes) between labeled source instances of seen classes and unlabelled target instances of unseen classes. Most existing ZSL approaches ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37

July 2015

2558 pages

Editors:
Francis Bach,
David Blei

Publisher

JMLR.org

Publication History

Published: 06 July 2015

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

70
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 05 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Yan JYin ZXu CDeng CHuang HSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Retrieval across any domains via large-scale pre-trained modelProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694374(55901-55912)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3694374
Astras NVogiatzis D(2024)Prediction of Drug-Drug Interactions with Zero-Shot LearningProceedings of the 13th Hellenic Conference on Artificial Intelligence10.1145/3688671.3688756(1-8)Online publication date: 11-Sep-2024
https://dl.acm.org/doi/10.1145/3688671.3688756
Chen CTang LHuang YHan XYu YOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)CODAProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3666682(12746-12759)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3666682
Nilforoshan HMoor MRoohani YChen YŚurina AYasunaga MOblak SLeskovec JOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Zero-shot causal learningProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3666423(6862-6901)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3666423
Wu LJiang JZhao HWang HLian DZhang MChen EElkind E(2023)KMFProceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/262(2361-2369)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.24963/ijcai.2023/262
Li XZhang YBian SQu YXie YShi ZFan JElkind E(2023)VS-BoostProceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/123(1107-1115)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.24963/ijcai.2023/123
Rao YYang ZZeng SWang QPu J(2023)Dual Projective Zero-Shot Learning Using Text DescriptionsACM Transactions on Multimedia Computing, Communications, and Applications10.1145/351424719:1(1-17)Online publication date: 5-Jan-2023
https://dl.acm.org/doi/10.1145/3514247
Mazzetto AMenghini CYuan AUpfal EBach SKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)Tight lower bounds on worst-case guarantees for zero-shot learning with attributesProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3601704(19732-19745)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3601704
Naeem MXian YVan Gool LTombari FKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)I2DFormerProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3601162(12283-12294)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3601162
Wang ZSun JKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)TransTabProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3600480(2902-2915)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3600480
Show More Cited By

View Options

View options

Figures

Tables

Media

View Table of Conten