零样本学习（Zero-Shot Learning）是AI识别方法之一。简单来说就是识别从未见过的数据类别，即训练的分类器不仅仅能够识别出训练集中已有的数据类别，还可以对于来自未见过的类别的数据进行区分。这是一个很有用的功能，使得计算机能够具有知识迁移的能力，并无需任何训练数据，很符合现实生活中海量类别的存在形式。
在传统图像识别任务中，训练阶段和测试阶段的类别是相同的，但每次为了识别新类别的样本需要在训练集中加入这种类别的数据。一些类别的样本收集代价大，即使收集到足够的训练样本，也需要对整个模型进行重新训练。这都会加大识别系统的成本，零样本学习方法便能很好的解决这个问题。
少样本学习（Few-shot learning）和零样本学习问题类似，只包含少量的学习样本。本文整理了零样本（zero-shot learning）或少样本（few-shot learning）学习相关最新的一些经典论文，重要的开源代码，数据集，以及其他一些预训练模型资源。
资源整理自网络，源地址：https://github.com/e-271/awesome-few-shot-learning
目录
重要论文
最新会议论文
数据集
开源代码
预训练模型
其他资源
重要论文
模型优化
•Unsupervised Meta-Learning for Few-Shot Image and Video Classification [Khodadadeh et al. 2018]
•A Simple Neural Attentive Meta-Learner [Mishra et al. 2018]
•Neural Optimizer Search with Reinforcement Learning [Bello 2017]
•Optimization as a Model for Few-Shot Learning [Ravi, Larochelle 2017]
•Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks [Finn et al. 2017]
评价指标学习
•TADAM: Task dependent adaptive metric for improved few-shot learning [Oreshkin et al. 2019]
•Learning to Compare: Relation Network for Few-Shot Learning [Sung et al. 2018]
•Meta-Learning for Semi-Supervised Few-Shot Classification [Triantafillou et al. 2018]
•Prototypical Networks for Few-shot Learning [Snell et al. 2017]
•Matching Networks for One Shot Learning [Vinyals et al. 2017]
•Transfer of View-Manifold Learning to Similarity Perception of Novel Objects [Lin et al. 2017]
•Generative Adversarial Residual Pairwise Networks for One Shot Learning [Mehrota & Dukkipatti 2017]
•Siamese Neural Networks for One-shot Image Recognition [Koch et al. 2015]
数据扩充
•Data Augmentation Generative Adversarial Networks [Antoniou et al. 2018]
•Low-Shot Learning from Imaginary Data [Wang et al. 2018]
•Low-shot Visual Recognition by Shrinking and Hallucinating Features [Hariharan, Girshick 2017]
注意力机制
•Dynamic Few-Shot Visual Learning without Forgetting [Gidaris & Komodakis 2018]
•Meta Networks [Munkhdalai & Yu 2017]
•One-shot Learning with Memory-Augmented Neural Networks [Santoro 2016]
最新会议论文
ICCV 2019
•CIZSL: Mohamed Elhoseiny, Mohamed Elfeki. "Creativity Inspired Zero-Shot Learning." ICCV (2019). [pdf]. [code]
•LFGAA+SA: Yang Liu, Jishun Guo, Deng Cai, Xiaofei He. "Attribute Attention for Semantic Disambiguation in Zero-Shot Learning." ICCV (2019). [pdf]. [code]
•TCN: Huajie Jiang, Ruiping Wang, Shiguang Shan, Xilin Chen. "Transferable Contrastive Network for Generalized Zero-Shot Learning." ICCV (2019). [pdf].
•GXE: Kai Li, Martin Renqiang Min, Yun Fu. "Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective." ICCV (2019). [pdf]
•Yizhe Zhu1, Jianwen Xie, Bingchen Liu, Ahmed Elgammal. "Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learning." ICCV (2019). [pdf]
•Yannick Le Cacheux, Herve Le Borgne, Michel Crucianu "Modeling Inter and Intra-Class Relations in the Triplet Loss for Zero-Shot Learning." ICCV (2019). [pdf].
CVPR 2019
•CADA-VAE: Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, Zeynep Akata. "Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders." CVPR (2019). [pdf] [code]
•GDAN: He Huang, Changhu Wang, Philip S. Yu, Chang-Dong Wang. "Generative Dual Adversarial Network for Generalized Zero-shot Learning." CVPR (2019). [pdf] [code]
•DeML: Binghui Chen, Weihong Deng. "Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval." CVPR (2019). [pdf] [code]
•Gzsl-VSE: Pengkai Zhu, Hanxiao Wang, Venkatesh Saligrama. "Generalized Zero-Shot Recognition based on Visually Semantic Embedding." CVPR (2019). [pdf]
•LisGAN: Jingjing Li, Mengmeng Jin, Ke Lu, Zhengming Ding, Lei Zhu, Zi Huang. "Leveraging the Invariant Side of Generative Zero-Shot Learning." CVPR (2019). [pdf] [code]
•DGP: Michael Kampffmeyer, Yinbo Chen, Xiaodan Liang, Hao Wang, Yujia Zhang, Eric P. Xing. "Rethinking Knowledge Graph Propagation for Zero-Shot Learning." CVPR (2019). [pdf] [code]
•DAZL: Yuval Atzmon, Gal Chechik. "Domain-Aware Generalized Zero-Shot Learning." CVPR (2019). [pdf]
•PrEN: Meng Ye, Yuhong Guo. "Progressive Ensemble Networks for Zero-Shot Recognition." CVPR (2019). [pdf]
•Tristan Hascoet, Yasuo Ariki, Tetsuya Takiguchi. "On Zero-Shot Learning of generic objects." CVPR (2019). [pdf] [code]
•SABR-T: Akanksha Paul, Naraynan C Krishnan, Prateek Munjal. "Semantically Aligned Bias Reducing Zero Shot Learning." CVPR (2019). [pdf]
•AREN: Guo-Sen Xie, Li Liu, Xiaobo Jin, Fan Zhu, Zheng Zhang, Jie Qin, Yazhou Yao, Ling Shao. "Attentive Region Embedding Network for Zero-shot Learning." CVPR (2019). [pdf] [code]
•Zhengming Ding, Hongfu Liu. "Marginalized Latent Semantic Encoder for Zero-Shot Learning." CVPR (2019). [pdf]
•PQZSL: Jin Li, Xuguang Lan, Yang Liu, Le Wang, Nanning Zheng. "Compressing Unknown Classes with Product Quantizer for Efficient Zero-Shot Classification." CVPR (2019). [pdf]
•Mert Bulent Sariyildiz, Ramazan Gokberk Cinbis. "Gradient Matching Generative Networks for Zero-Shot Learning." CVPR (2019). [pdf]
•Bin Tong, Chao Wang, Martin Klinkigt, Yoshiyuki Kobayashi, Yuuichi Nonaka. "Hierarchical Disentanglement of Discriminative Latent Features for Zero-shot Learning." CVPR (2019). [pdf]
NeurIPS 2018
•DCN: Shichen Liu, Mingsheng Long, Jianmin Wang, Michael I. Jordan."Generalized Zero-Shot Learning with Deep Calibration Network" NeurIPS (2018). [pdf]
•S2GA: Yunlong Yu, Zhong Ji, Yanwei Fu, Jichang Guo, Yanwei Pang, Zhongfei (Mark) Zhang."Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning." NeurIPS (2018). [pdf]
•DIPL: An Zhao, Mingyu Ding, Jiechao Guan, Zhiwu Lu, Tao Xiang, Ji-Rong Wen "Domain-Invariant Projection Learning for Zero-Shot Recognition." NeurIPS (2018). [pdf]
ECCV 2018
•SZSL: Jie Song, Chengchao Shen, Jie Lei, An-Xiang Zeng, Kairi Ou, Dacheng Tao, Mingli Song. "Selective Zero-Shot Classification with Augmented Attributes." ECCV (2018). [pdf]
•LCP-SA: Huajie Jiang, Ruiping Wang, Shiguang Shan, Xilin Chen. "Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition." ECCV (2018). [pdf]
•MC-ZSL: Rafael Felix, Vijay Kumar B. G., Ian Reid, Gustavo Carneiro. "Multi-modal Cycle-consistent Generalized Zero-Shot Learning." ECCV (2018). [pdf] [code]
CVPR 2018
•GCN: Xiaolong Wang, Yufei Ye, Abhinav Gupta. "Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs." CVPR (2018). [pdf] [code]
•PSR: Yashas Annadani, Soma Biswas. "Preserving Semantic Relations for Zero-Shot Learning." CVPR (2018). [pdf]
•GAN-NT: Yizhe Zhu, Mohamed Elhoseiny, Bingchen Liu, Xi Peng, Ahmed Elgammal. "A Generative Adversarial Approach for Zero-Shot Learning From Noisy Texts." CVPR (2018). [pdf]
•TUE: Jie Song, Chengchao Shen, Yezhou Yang, Yang Liu, Mingli Song. "Transductive Unbiased Embedding for Zero-Shot Learning." CVPR (2018). [pdf]
•SP-AEN: Long Chen, Hanwang Zhang, Jun Xiao, Wei Liu, Shih-Fu Chang. "Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks." CVPR (2018). [pdf] [code]
•ML-SKG: Chung-Wei Lee, Wei Fang, Chih-Kuan Yeh, Yu-Chiang Frank Wang. "Multi-Label Zero-Shot Learning With Structured Knowledge Graphs." CVPR (2018). [pdf] [project]
•GZSL-SE: Vinay Kumar Verma, Gundeep Arora, Ashish Mishra, Piyush Rai. "Generalized Zero-Shot Learning via Synthesized Examples." CVPR (2018). [pdf]
•FGN: Yongqin Xian, Tobias Lorenz, Bernt Schiele, Zeynep Akata. "Feature Generating Networks for Zero-Shot Learning." CVPR (2018). [pdf] [code] [project]
•LDF: Yan Li, Junge Zhang, Jianguo Zhang, Kaiqi Huang. "Discriminative Learning of Latent Features for Zero-Shot Recognition." CVPR (2018). [pdf]
•WSL: Li Niu, Ashok Veeraraghavan, and Ashu Sabharwal. "Webly Supervised Learning Meets Zero-shot Learning: A Hybrid Approach for Fine-grained Classification." CVPR (2018). [pdf]
TPAMI 2018
•C-GUB: Yongqin Xian, Christoph H. Lampert, Bernt Schiele, Zeynep Akata. "Zero-shot learning-A comprehensive evaluation of the good, the bad and the ugly." TPAMI (2018). [pdf] [project]
AAAI 2018, 2017
•GANZrl: Bin Tong, Martin Klinkigt, Junwen Chen, Xiankun Cui, Quan Kong, Tomokazu Murakami, Yoshiyuki Kobayashi. "Adversarial Zero-shot Learning With Semantic Augmentation." AAAI (2018). [pdf]
•JDZsL: Soheil Kolouri, Mohammad Rostami, Yuri Owechko, Kyungnam Kim. "Joint Dictionaries for Zero-Shot Learning." AAAI (2018). [pdf]
•VZSL: Wenlin Wang, Yunchen Pu, Vinay Kumar Verma, Kai Fan, Yizhe Zhang, Changyou Chen, Piyush Rai, Lawrence Carin. "Zero-Shot Learning via Class-Conditioned Deep Generative Models." AAAI (2018). [pdf]
•AS: Yuchen Guo, Guiguang Ding, Jungong Han, Sheng Tang. "Zero-Shot Learning With Attribute Selection." AAAI (2018). [pdf]
•DSSC: Yan Li, Zhen Jia, Junge Zhang, Kaiqi Huang, Tieniu Tan."Deep Semantic Structural Constraints for Zero-Shot Learning." AAAI (2018). [pdf]
•ZsRDA: Yang Long, Li Liu, Yuming Shen, Ling Shao. "Towards Affordable Semantic Searching: Zero-Shot Retrieval via Dominant Attributes." AAAI (2018). [pdf]
•DCL: Yuchen Guo, Guiguang Ding, Jungong Han, Yue Gao. "Zero-Shot Recognition via Direct Classifier Learning with Transferred Samples and Pseudo Labels." AAAI (2017). [pdf]
ICCV 2017
•A2C: Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis. "Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning." ICCV (2017). [pdf] [code]
•PVE: Soravit Changpinyo, Wei-Lun Chao, Fei Sha. "Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning." ICCV (2017). [pdf][code]
•LDL: Huajie Jiang, Ruiping Wang, Shiguang Shan, Yi Yang, Xilin Chen. "Learning Discriminative Latent Attributes for Zero-Shot Classification." ICCV (2017). [pdf]]
CVPR 2017
•Deep-SCoRe: Pedro Morgado, Nuno Vasconcelos."Semantically Consistent Regularization for Zero-Shot Recognition." CVPR (2017). [pdf] [code]
•DEM: Li Zhang, Tao Xiang, Shaogang Gong. "Learning a Deep Embedding Model for Zero-Shot Learning." CVPR (2017). [pdf] [code]
•VDS: Yang Long, Li Liu, Ling Shao, Fumin Shen, Guiguang Ding, Jungong Han. "From Zero-Shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis." CVPR (2017). [pdf]
•ESD: Zhengming Ding, Ming Shao, Yun Fu. "Low-Rank Embedded Ensemble Semantic Dictionary for Zero-Shot Learning." CVPR (2017). [pdf]
•SAE: Elyor Kodirov, Tao Xiang, Shaogang Gong. "Semantic Autoencoder for Zero-Shot Learning." CVPR (2017). [pdf][code]
•DVSM: Yanan Li, Donghui Wang, Huanhang Hu, Yuetan Lin, Yueting Zhuang. "Zero-Shot Recognition Using Dual Visual-Semantic Mapping Paths". CVPR (2017). [pdf]
•MTF-MR: Xing Xu, Fumin Shen, Yang Yang, Dongxiang Zhang, Heng Tao Shen, Jingkuan Song. "Matrix Tri-Factorization With Manifold Regularizations for Zero-Shot Learning." CVPR (2017). [pdf]
•Nour Karessli, Zeynep Akata, Bernt Schiele, Andreas Bulling. "Gaze Embeddings for Zero-Shot Image Classification." CVPR (2017). [pdf] [code]
•GUB: Yongqin Xian, Bernt Schiele, Zeynep Akata. "Zero-Shot learning - The Good, the Bad and the Ugly." CVPR (2017).[pdf] [code]
CVPR 2016
•MC-ZSL: Zeynep Akata, Mateusz Malinowski, Mario Fritz, Bernt Schiele. "Multi-Cue Zero-Shot Learning With Strong Supervision." CVPR (2016). [pdf] [code]
•LATEM: Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh Nguyen, Matthias Hein, Bernt Schiele. "Latent Embeddings for Zero-Shot Classification." CVPR (2016). [pdf][code]
•LIM: Ruizhi Qiao, Lingqiao Liu, Chunhua Shen, Anton van den Hengel. "Less Is More: Zero-Shot Learning From Online Textual Documents With Noise Suppression." CVPR (2016). [pdf]
•SYNC: Soravit Changpinyo, Wei-Lun Chao, Boqing Gong, Fei Sha. "Synthesized Classifiers for Zero-Shot Learning." CVPR (2016). [pdf][code]
•RML: Ziad Al-Halah, Makarand Tapaswi, Rainer Stiefelhagen. "Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning." CVPR (2016). [pdf]
•SLE: Ziming Zhang, Venkatesh Saligrama. "Zero-Shot Learning via Joint Latent Similarity Embedding." CVPR (2016). [pdf] [code]
ECCV 2016
•Wei-Lun Chao, Soravit Changpinyo, Boqing Gong2, Fei Sha. "An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild." ECCV (2016). [pdf]
•MTE: Xun Xu, Timothy M. Hospedales, Shaogang Gong. "Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation." ECCV (2016). [pdf]
•Ziming Zhang, Venkatesh Saligrama."Zero-Shot Recognition via Structured Prediction." ECCV (2016). [pdf]
•Maxime Bucher, Stephane Herbin, Frederic Jurie."Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification." ECCV (2016). [pdf]
AAAI 2016
•RKT: Donghui Wang, Yanan Li, Yuetan Lin, Yueting Zhuang. "Relational Knowledge Transfer for Zero-Shot Learning." AAAI (2016). [pdf]
TPAMI 2016, 2015, 2013
•ALE: Zeynep Akata, Florent Perronnin, Zaid Harchaoui, and Cordelia Schmid. "Label-Embedding for Image Classification." TPAMI (2016). [pdf]
•TMV: Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Shaogang Gong. "Transductive Multi-view Zero-Shot Learning." TPAMI (2015) [pdf] [code]
•DAP: Christoph H. Lampert, Hannes Nickisch and Stefan Harmeling. "Attribute-Based Classification for Zero-Shot Visual Object Categorization." TPAMI (2013) [pdf]
CVPR 2015
•SJE: Zeynep Akata, Scott Reed, Daniel Walter, Honglak Lee, Bernt Schiele. "Evaluation of Output Embeddings for Fine-Grained Image Classification." CVPR (2015). [pdf] [code]
•Zhenyong Fu, Tao Xiang, Elyor Kodirov, Shaogang Gong. "Zero-Shot Object Recognition by Semantic Manifold Distance." CVPR (2015). [pdf]
ICCV 2015
•SSE: Ziming Zhang, Venkatesh Saligrama. "Zero-Shot Learning via Semantic Similarity Embedding." ICCV (2015). [pdf][code]
•LRL: Xin Li, Yuhong Guo, Dale Schuurmans."Semi-Supervised Zero-Shot Classification with Label Representation Learning." ICCV (2015). [pdf]
•UDA: Elyor Kodirov, Tao Xiang, Zhenyong Fu, Shaogang Gong. "Unsupervised Domain Adaptation for Zero-Shot Learning." ICCV (2015). [pdf]
•Jimmy Lei Ba, Kevin Swersky, Sanja Fidler, Ruslan Salakhutdinov. "Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions." ICCV (2015). [pdf]
NIPS 2014, 2013, 2009
•Dinesh Jayram, Kristen Grauman."Zero-Shot Recognition with Unreliable Attributes" NIPS (2014) [pdf]
•CMT: Richard Socher, Milind Ganjoo, Christopher D. Manning, Andrew Y. Ng. "Zero-Shot Learning Through Cross-Modal Transfer" NIPS (2013) [pdf] [code]
•DeViSE: Andrea Frome, Greg S. Corrado, Jonathon Shlens, Samy Bengio, Jeffrey Dean, Marc’Aurelio Ranzato, Tomas Mikolov."DeViSE: A Deep Visual-Semantic Embedding Model" NIPS (2013) [pdf]
•Mark Palatucci, Dean Pomerleau, Geoffrey Hinton, Tom M. Mitchell. "Zero-Shot Learning with Semantic Output Codes" NIPS (2009) [pdf]
ECCV 2014
•TMV-BLP: Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Zhenyong Fu, Shaogang Gong. "Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation" ECCV (2014).[pdf] [code]
•Stanislaw Antol, Larry Zitnick, Devi Parikh. "Zero-Shot Learning via Visual Abstraction." ECCV (2014). [pdf] [code] [project]
CVPR 2013
•ALE: Z.Akata, F. Perronnin, Z. Harchaoui, and C. Schmid. "Label Embedding for Attribute-Based Classification." CVPR (2013). [pdf]
Other Papers
•EsZSL: Bernardino Romera-Paredes, Philip H. S. Torr. "An embarrassingly simple approach to zero-shot learning." ICML (2015). [pdf] [Code]
•AEZSL: "Zero-Shot Learning via Category-Specific Visual-Semantic Mapping and Label Refinement" IEEE SPS (2018). [pdf]
•ZSGD: Tiancheng Zhao, Maxine Eskenazi. "Zero-Shot Dialog Generation with Cross-Domain Latent Actions" SIGDIAL (2018). [pdf] [code]
•Yanwei Fu, Tao Xiang, Yu-Gang Jiang, Xiangyang Xue, Leonid Sigal, Shaogang Gong "Recent Advances in Zero-shot Recognition". IEEE Signal Processing Magazine. [pdf]
•Michael Kampffmeyer, Yinbo Chen, Xiaodan Liang, Hao Wang, Yujia Zhang, Eric P. Xing "Rethinking Knowledge Graph Propagation for Zero-Shot Learning" arXiv (2018). [pdf] [code]
•Survey: Wei Wang, Vincent W. Zheng, Han Yu, Chunyan Miao. "A Survey of Zero-Shot Learning: Settings, Methods, and Applications". TIST (2019). [pdf]
数据集
•LAD: Large-scale Attribute Dataset. Categories:230. [link]
•CUB: Caltech-UCSD Birds. Categories:200. [link]
•AWA2: Animals with Attributes. Categories:50. [link]
•aPY: attributes Pascal and Yahoo. Categories:32 [link]
•Flowers Dataset: There are two datasets, Categories: 17 and 102. [link]
•SUN: Scene Attributes. Categories:717. [link]
开源代码
This repository contains a Demo folder which has a Jupyter Notebook step-by-step code to "An embarrassingly simple approach to zero-shot learning." ICML (2015). This can be used as an introductory code to obtain the basic understanding of Zero-shot Learning.
更多NLP、CV、机器学习论文和资源，扫描二维码关注微信公众号，回复关键字“机器学习要领”获取下载地址。
任何关于算法、编程、AI行业知识或博客内容的问题，可以随时扫码关注公众号「图灵的猫」，加入”学习小组“，沙雕博主在线答疑~此外，公众号内还有更多AI、算法、编程和大数据知识分享，以及免费的SSR节点和学习资料。其他平台（知乎/B站）也是同名「图灵的猫」，不要迷路哦~
