ABSTRACT
Recently, feature generating methods have been successfully applied to zero-shot learning (ZSL). However, most previous approaches only generate visual representations for zero-shot recognition. In fact, typical ZSL is a classic multi-modal learning protocol which consists of a visual space and a semantic space. In this paper, therefore, we present a new method which can simultaneously generate both visual representations and semantic representations so that the essential multi-modal information associated with unseen classes can be captured. Specifically, we address the most challenging issue in such a paradigm, i.e., how to handle the domain shift and thus guarantee that the learned representations are modality-invariant. To this end, we propose two strategies: 1) leveraging the mutual information between the latent visual representations and the semantic representations; 2) maximizing the entropy of the joint distribution of the two latent representations. By leveraging the two strategies, we argue that the two modalities can be well aligned. At last, extensive experiments on five widely used datasets verify that the proposed method is able to significantly outperform previous the state-of-the-arts.
Supplemental Material
- Zeynep Akata, Florent Perronnin, Zaid Harchaoui, and Cordelia Schmid. 2016. Label-embedding for image classification. IEEE TPAMI, Vol. 38, 7 (2016), 1425--1438.Google ScholarCross Ref
- Zeynep Akata, Scott Reed, Daniel Walter, Honglak Lee, and Bernt Schiele. 2015. Evaluation of output embeddings for fine-grained image classification. In CVPR. 2927--2936.Google Scholar
- Sanjeev Arora, Rong Ge, Yingyu Liang, Tengyu Ma, and Yi Zhang. 2017. Generalization and equilibrium in generative adversarial nets (gans). In ICML. JMLR. org, 224--232.Google Scholar
- Yuval Atzmon and Gal Chechik. 2019. Adaptive Confidence Smoothing for Generalized Zero-Shot Learning. In CVPR. 11671--11680.Google Scholar
- Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, and R Devon Hjelm. 2018. Mine: mutual information neural estimation. arXiv preprint arXiv:1801.04062 (2018).Google Scholar
- Shai Ben-David, John Blitzer, Koby Crammer, Alex Kulesza, Fernando Pereira, and Jennifer Wortman Vaughan. 2010. A theory of learning from different domains. Machine learning, Vol. 79, 1--2 (2010), 151--175.Google Scholar
- Samuel R Bowman, Luke Vilnis, Oriol Vinyals, Andrew M Dai, Rafal Jozefowicz, and Samy Bengio. 2015. Generating sentences from a continuous space. arXiv preprint arXiv:1511.06349 (2015).Google Scholar
- Soravit Changpinyo, Wei-Lun Chao, Boqing Gong, and Fei Sha. 2016. Synthesized classifiers for zero-shot learning. In CVPR. 5327--5336.Google Scholar
- Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, and Pieter Abbeel. 2016. Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In NeurIPS. 2172--2180.Google Scholar
- Zhi Chen, Jingjing Li, Yadan Luo, Zi Huang, and Yang Yang. 2020. Canzsl: Cycle-consistent adversarial networks for zero-shot learning from natural language. In WACV. 874--883.Google Scholar
- Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In CVPR. 248--255.Google Scholar
- Zhengming Ding, Ming Shao, and Yun Fu. 2017. Low-Rank Embedded Ensemble Semantic Dictionary for Zero-Shot Learning. In CVPR. IEEE.Google Scholar
- Zhengming Ding, Ming Shao, and Yun Fu. 2018. Generative zero-shot learning via low-rank embedded semantic dictionary. IEEE TPAMI (2018).Google Scholar
- Rafael Felix, Vijay BG Kumar, Ian Reid, and Gustavo Carneiro. 2018. Multi-modal cycle-consistent generalized zero-shot learning. In ECCV. 21--37.Google Scholar
- Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Tomas Mikolov, et almbox. 2013. Devise: A deep visual-semantic embedding model. In NIPS. 2121--2129.Google Scholar
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In NIPS. 2672--2680.Google Scholar
- Arthur Gretton, Karsten M Borgwardt, Malte J Rasch, Bernhard Schölkopf, and Alexander Smola. 2012. A kernel two-sample test. JMLR, Vol. 13, Mar (2012), 723--773.Google Scholar
- R Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Adam Trischler, and Yoshua Bengio. 2019. Learning deep representations by mutual information estimation and maximization. ICLR (2019).Google Scholar
- He Huang, Changhu Wang, Philip S Yu, and Chang-Dong Wang. 2019. Generative Dual Adversarial Network for Generalized Zero-shot Learning. In CVPR. 801--810.Google Scholar
- Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. 2017. Image-to-image translation with conditional adversarial networks. In CVPR. 1125--1134.Google Scholar
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013).Google Scholar
- Elyor Kodirov, Tao Xiang, Zhenyong Fu, and Shaogang Gong. 2015. Unsupervised domain adaptation for zero-shot learning. In ICCV. 2452--2460.Google Scholar
- Elyor Kodirov, Tao Xiang, and Shaogang Gong. 2017. Semantic Autoencoder for Zero-Shot Learning. arXiv preprint arXiv:1704.08345 (2017).Google Scholar
- Christoph H Lampert, Hannes Nickisch, and Stefan Harmeling. 2009. Learning to detect unseen object classes by between-class attribute transfer. In CVPR. IEEE, 951--958.Google Scholar
- Jingjing Li, Erpeng Chen, Zhengming Ding, Lei Zhu, Ke Lu, and Zi Huang. 2019 a. Cycle-consistent conditional adversarial transfer networks. In ACM MM. 747--755.Google Scholar
- Jingjing Li, Erpeng Chen, Zhengming Ding, Lei Zhu, Ke Lu, and Heng Tao Shen. 2020. Maximum Density Divergence for Domain Adaptation. IEEE TPAMI (2020).Google Scholar
- Jingjing Li, Mengmeng Jing, Ke Lu, Zhengming Ding, Lei Zhu, and Zi Huang. 2019 b. Leveraging the Invariant Side of Generative Zero-Shot Learning. In CVPR. 7402--7411.Google Scholar
- Jingjing Li, Mengmeng Jing, Ke Lu, Lei Zhu, Yang Yang, and Zi Huang. 2019 c. Alleviating Feature Confusion for Generative Zero-shot Learning. In ACM MM. 1587--1595.Google Scholar
- Jingjing Li, Mengmeng Jing, Ke Lu, Lei Zhu, Yang Yang, and Zi Huang. 2019 d. From Zero-Shot Learning to Cold-Start Recommendation. AAAI (2019).Google Scholar
- Kai Li, Martin Renqiang Min, and Yun Fu. 2019 e. Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective. In ICCV. 3583--3592.Google Scholar
- Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. JMLR, Vol. 9, Nov (2008), 2579--2605.Google Scholar
- Ashish Mishra, M Reddy, Anurag Mittal, and Hema A Murthy. 2018. A generative model for zero shot learning using conditional variational autoencoders. In CVPR.Google Scholar
- Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2019. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2019).Google Scholar
- Genevieve Patterson and James Hays. 2012. Sun attribute database: Discovering, annotating, and recognizing scene attributes. In CVPR. IEEE, 2751--2758.Google Scholar
- Bernardino Romera-Paredes and Philip Torr. 2015. An embarrassingly simple approach to zero-shot learning. In ICML. 2152--2161.Google Scholar
- Edgar Schonfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, and Zeynep Akata. 2019. Generalized zero-and few-shot learning via aligned variational autoencoders. In CVPR. 8247--8255.Google Scholar
- Yao-Hung Hubert Tsai, Liang-Kang Huang, and Ruslan Salakhutdinov. 2017. Learning robust visual-semantic embeddings. In ICCV. IEEE, 3591--3600.Google Scholar
- V Kumar Verma, Gundeep Arora, Ashish Mishra, and Piyush Rai. 2018. Generalized zero-shot learning via synthesized examples. In CVPR.Google Scholar
- Paul Viola and William M Wells III. 1997. Alignment by maximization of mutual information. IJCV, Vol. 24, 2 (1997), 137--154.Google ScholarDigital Library
- Yongqin Xian, Tobias Lorenz, Bernt Schiele, and Zeynep Akata. 2018a. Feature generating networks for zero-shot learning. In CVPR.Google Scholar
- Yongqin Xian, Bernt Schiele, and Zeynep Akata. 2018b. Zero-Shot Learning-A Comprehensive Evaluation of The Good, the Bad and the Ugly. TPAMI (2018).Google Scholar
- Meng Ye and Yuhong Guo. 2019. Progressive Ensemble Networks for Zero-Shot Recognition. In CVPR . 11728--11736.Google Scholar
- Li Zhang, Tao Xiang, Shaogang Gong, et almbox. 2017. Learning a deep embedding model for zero-shot learning. (2017).Google Scholar
- Yizhe Zhu, Mohamed Elhoseiny, Bingchen Liu, Xi Peng, and Ahmed Elgammal. 2018. A generative adversarial approach for zero-shot learning from noisy texts. In CVPR .Google Scholar
Index Terms
- Learning Modality-Invariant Latent Representations for Generalized Zero-shot Learning
Recommendations
Transductive Visual-Semantic Embedding for Zero-shot Learning
ICMR '17: Proceedings of the 2017 ACM on International Conference on Multimedia RetrievalZero-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 ...
Multi-label Generalized Zero-Shot Learning Using Identifiable Variational Autoencoders
Extended RealityAbstractMulti-label Zero-Shot Learning (ZSL) is an extension of traditional single-label ZSL, where the objective is to accurately classify images containing multiple unseen classes that are not available during training. Current techniques depends on ...
Transductive Multi-View Zero-Shot Learning
Most existing zero-shot learning approaches exploit transfer learning via an intermediate semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A projection from a low-level ...
Comments