2020年最全-少样本学习（FSL）相关综述、数据集、模型/算法和应用资源整理分享

作者：lqfarmer
链接：https://zhuanlan.zhihu.com/p/146207227
来源：知乎
著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处。

Few Shot Learning（FSL）又称少样本学习，这是做AI研究经常遇到的一个问题。深度学习技术需要大量的数据来训练一个好的模型。例如典型的 MNIST 分类问题，一共有 10 个类，训练集一共有 6000 个样本，平均下来每个类大约 600 个样本，但是我们想一下我们人类自己，我们区分 0 到 9 的数字图片的时候需要看 6000 张图片才知道怎么区分吗？很显然，不需要！这表明当前的深度学习技术和我们人类智能差距还是很大的，要想弥补这一差距，少样本学习是一个很关键的问题。

另外还有一个重要原因是如果想要构建新的数据集，还是举分类数据集为例，我们需要标记大量的数据，但是有的时候标记数据集需要某些领域的专家（例如医学图像的标记），这费时又费力，因此如果我们可以解决少样本学习问题，只需要每个类标记几张图片就可以高准确率的给剩余大量图片自动标记。

基于以上两个重要的的原因，少样本学习是一个非常吸引人且具有非常重要研究意义，工业实用价值的一个领域，本资源整理了近几年在深度学习领域，少样本学习相关综述、数据集、模型/算法和应用资源，分享给大家。

资源整理自网络，源地址：https://github.com/tata1661/FewShotPapers

综述论文

相关数据集

相关模型

多任务学习

嵌入学习

利用外部记忆学习

生成建模

算法相关

Fine tuning现有参数

Fine tuning元学习参数

参数学习搜索

应用场景

计算机视觉

机器人学

自然语言处理

声音信号处理

其他

理论研究相关

综述论文

Generalizing from a few examples: A survey on few-shot learning, CSUR, 2020 Y. Wang, Q. Yao, J. T. Kwok, and L. M. Ni.

相关数据集

Learning from one example through shared densities on transforms, in CVPR, 2000. E. G. Miller, N. E. Matsakis, and P. A. Viola.

Domain-adaptive discriminative one-shot learning of gestures, in ECCV, 2014. T. Pfister, J. Charles, and A. Zisserman.

One-shot learning of scene locations via feature trajectory transfer, in CVPR, 2016. R. Kwitt, S. Hegenbart, and M. Niethammer.

Low-shot visual recognition by shrinking and hallucinating features, in ICCV, 2017. B. Hariharan and R. Girshick.

Improving one-shot learning through fusing side information, arXiv preprint, 2017. Y.H.Tsai and R.Salakhutdinov.

Fast parameter adaptation for few-shot image captioning and visual question answering, in ACM MM, 2018. X. Dong, L. Zhu, D. Zhang, Y. Yang, and F. Wu.

Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning, in CVPR, 2018. Y. Wu, Y. Lin, X. Dong, Y. Yan, W. Ouyang, and Y. Yang.

Low-shot learning with large-scale diffusion, in CVPR, 2018. M. Douze, A. Szlam, B. Hariharan, and H. Jégou.

Diverse few-shot text classification with multiple metrics, in NAACL-HLT, 2018. M. Yu, X. Guo, J. Yi, S. Chang, S. Potdar, Y. Cheng, G. Tesauro, H. Wang, and B. Zhou.

Delta-encoder: An effective sample synthesis method for few-shot object recognition, in NeurIPS, 2018. E. Schwartz, L. Karlinsky, J. Shtok, S. Harary, M. Marder, A. Kumar, R. Feris, R. Giryes, and A. Bronstein.

Low-shot learning via covariance-preserving adversarial augmentation networks, in NeurIPS, 2018. H. Gao, Z. Shou, A. Zareian, H. Zhang, and S. Chang.

AutoAugment: Learning augmentation policies from data, in CVPR, 2019. E. D. Cubuk, B. Zoph, D. Mane, V. Vasudevan, and Q. V. Le.

EDA: Easy data augmentation techniques for boosting performance on text classification tasks, in EMNLP and IJCNLP, 2019. J. Wei and K. Zou.

相关模型

多任务学习

Multi-task transfer methods to improve one-shot learning for multimedia event detection, in BMVC, 2015. W. Yan, J. Yap, and G. Mori.

Label efficient learning of transferable representations acrosss domains and tasks, in NeurIPS, 2017. Z. Luo, Y. Zou, J. Hoffman, and L. Fei-Fei.

Multi-content GAN for few-shot font style transfer, in CVPR, 2018. S. Azadi, M. Fisher, V. G. Kim, Z. Wang, E. Shechtman, and T. Darrell.

Feature space transfer for data augmentation, in CVPR, 2018. B. Liu, X. Wang, M. Dixit, R. Kwitt, and N. Vasconcelos.

One-shot unsupervised cross domain translation, in NeurIPS, 2018. S. Benaim and L. Wolf.

Fine-grained visual categorization using meta-learning optimization with sample selection of auxiliary data, in ECCV, 2018. Y. Zhang, H. Tang, and K. Jia.

Few-shot charge prediction with discriminative legal attributes, in COLING, 2018. Z. Hu, X. Li, C. Tu, Z. Liu, and M. Sun.

Few-shot adversarial domain adaptation, in NeurIPS, 2017. S. Motiian, Q. Jones, S. Iranmanesh, and G. Doretto.

嵌入学习

Object classification from a single example utilizing class relevance metrics, in NeurIPS, 2005.* M. Fink.

Few-shot learning through an information retrieval lens, in NeurIPS, 2017. E. Triantafillou, R. Zemel, and R. Urtasun.

Optimizing one-shot recognition with micro-set learning, in CVPR, 2010. K. D. Tang, M. F. Tappen, R. Sukthankar, and C. H. Lampert.

Siamese neural networks for one-shot image recognition, ICML deep learning workshop, 2015. G. Koch, R. Zemel, and R. Salakhutdinov

Matching networks for one shot learning, in NeurIPS, 2016. O. Vinyals, C. Blundell, T. Lillicrap, D. Wierstra et al.

Learning feed-forward one-shot learners, in NeurIPS, 2016. L. Bertinetto, J. F. Henriques, J. Valmadre, P. Torr, and A. Vedaldi.

Low data drug discovery with one-shot learning, ACS Central Science, 2017. H. Altae-Tran, B. Ramsundar, A. S. Pappu, and V. Pande.

Prototypical networks for few-shot learning, in NeurIPS, 2017. J. Snell, K. Swersky, and R. S. Zemel.

Attentive recurrent comparators, in ICML, 2017. P. Shyam, S. Gupta, and A. Dukkipati.

Learning algorithms for active learning, in ICML, 2017. P. Bachman, A. Sordoni, and A. Trischler.

Active one-shot learning, arXiv preprint, 2017. M. Woodward and C. Finn.

Structured set matching networks for one-shot part labeling, in CVPR, 2018. J. Choi, J. Krishnamurthy, A. Kembhavi, and A. Farhadi.

Low-shot learning from imaginary data, in CVPR, 2018. Y.-X. Wang, R. Girshick, M. Hebert, and B. Hariharan.

Learning to compare: Relation network for few-shot learning, in CVPR, 2018. F. Sung, Y. Yang, L. Zhang, T. Xiang, P. H. Torr, and T. M. Hospedales.

Dynamic conditional networks for few-shot learning, in ECCV, 2018. F. Zhao, J. Zhao, S. Yan, and J. Feng.

Tadam: Task dependent adaptive metric for improved few-shot learning, in NeurIPS, 2018. B. Oreshkin, P. R. López, and A. Lacoste.

Meta-learning for semi- supervised few-shot classification, in ICLR, 2018. M. Ren, S. Ravi, E. Triantafillou, J. Snell, K. Swersky, J. B. Tenen- baum, H. Larochelle, and R. S. Zemel.

Few-shot learning with graph neural networks, in ICLR, 2018. V. G. Satorras and J. B. Estrach.

A simple neural attentive meta-learner, in ICLR, 2018. N. Mishra, M. Rohaninejad, X. Chen, and P. Abbeel.

Meta-learning with differentiable closed-form solvers, in ICLR, 2019. L. Bertinetto, J. F. Henriques, P. Torr, and A. Vedaldi.

Learning to propopagate labels: Transductive propagation network for few-shot learning, in ICLR, 2019. Y. Liu, J. Lee, M. Park, S. Kim, E. Yang, S. Hwang, and Y. Yang.

利用外部记忆学习

Meta-learning with memory-augmented neural networks, in ICML, 2016. A. Santoro, S. Bartunov, M. Botvinick, D. Wierstra, and T. Lillicrap.

Few-shot object recognition from machine-labeled web images, in CVPR, 2017. Z. Xu, L. Zhu, and Y. Yang.

Learning to remember rare events, in ICLR, 2017. Ł. Kaiser, O. Nachum, A. Roy, and S. Bengio.

Meta networks, in ICML, 2017. T. Munkhdalai and H. Yu.

Memory matching networks for one-shot image recognition, in CVPR, 2018. Q. Cai, Y. Pan, T. Yao, C. Yan, and T. Mei.

Compound memory networks for few-shot video classification, in ECCV, 2018. L. Zhu and Y. Yang.

Memory, show the way: Memory based few shot word representation learning, in EMNLP, 2018. J. Sun, S. Wang, and C. Zong.

Rapid adaptation with conditionally shifted neurons, in ICML, 2018. T. Munkhdalai, X. Yuan, S. Mehri, and A. Trischler.

Adaptive posterior learning: Few-shot learning with a surprise-based memory module, in ICLR, 2019. T. Ramalho and M. Garnelo.

生成建模

One-shot learning of object categories, TPAMI, 2006. L. Fei-Fei, R. Fergus, and P. Perona.

Learning to learn with compound HD models, in NeurIPS, 2011. A. Torralba, J. B. Tenenbaum, and R. R. Salakhutdinov.

One-shot learning with a hierarchical nonparametric bayesian model, in ICML Workshop on Unsupervised and Transfer Learning, 2012. R. Salakhutdinov, J. Tenenbaum, and A. Torralba.

Human-level concept learning through probabilistic program induction, Science, 2015. B. M. Lake, R. Salakhutdinov, and J. B. Tenenbaum.

One-shot generalization in deep generative models, in ICML, 2016. D. Rezende, I. Danihelka, K. Gregor, and D. Wierstra.

One-shot video object segmentation, in CVPR, 2017. S. Caelles, K.-K. Maninis, J. Pont-Tuset, L. Leal-Taixe ́, D. Cremers, and L. Van Gool.

Towards a neural statistician, in ICLR, 2017. H. Edwards and A. Storkey.

Extending a parser to distant domains using a few dozen partially annotated examples, in ACL, 2018. V. Joshi, M. Peters, and M. Hopkins.

MetaGAN: An adversarial approach to few-shot learning, in NeurIPS, 2018. R. Zhang, T. Che, Z. Ghahramani, Y. Bengio, and Y. Song.

Few-shot autoregressive density estimation: Towards learning to learn distributions, in ICLR, 2018. S. Reed, Y. Chen, T. Paine, A. van den Oord, S. M. A. Eslami, D. Rezende, O. Vinyals, and N. de Freitas.

The variational homoencoder: Learning to learn high capacity generative models from few examples, in UAI, 2018. L. B. Hewitt, M. I. Nye, A. Gane, T. Jaakkola, and J. B. Tenenbaum.

Meta-learning probabilistic inference for prediction, in ICLR, 2019. J. Gordon, J. Bronskill, M. Bauer, S. Nowozin, and R. Turner.

算法相关

Fine tuning现有参数

Cross-generalization: Learning novel classes from a single example by feature replacement, in CVPR, 2005. E. Bart and S. Ullman.

One-shot adaptation of supervised deep convolutional models, in ICLR, 2013. J. Hoffman, E. Tzeng, J. Donahue, Y. Jia, K. Saenko, and T. Darrell.

Learning to learn: Model regression networks for easy small sample learning, in ECCV, 2016. Y.-X. Wang and M. Hebert.

Learning from small sample sets by combining unsupervised meta-training with CNNs, in NeurIPS, 2016. Y.-X. Wang and M. Hebert.

Efficient k-shot learning with regularized deep networks, in AAAI, 2018. D. Yoo, H. Fan, V. N. Boddeti, and K. M. Kitani.

CLEAR: Cumulative learning for one-shot one-class image recognition, in CVPR, 2018. J. Kozerawski and M. Turk.

Learning structure and strength of CNN filters for small sample size training, in CVPR, 2018. R. Keshari, M. Vatsa, R. Singh, and A. Noore.

Dynamic few-shot visual learning without forgetting, in CVPR, 2018. S. Gidaris and N. Komodakis.

Low-shot learning with imprinted weights, in CVPR, 2018. H. Qi, M. Brown, and D. G. Lowe.

Neural voice cloning with a few samples, in NeurIPS, 2018. S.Arik,J.Chen,K.Peng,W.Ping,andY.Zhou.

Fine tuning元学习参数

Model-agnostic meta-learning for fast adaptation of deep networks, in ICML, 2017. C. Finn, P. Abbeel, and S. Levine.

Bayesian model-agnostic meta-learning, in NeurIPS, 2018. J. Yoon, T. Kim, O. Dia, S. Kim, Y. Bengio, and S. Ahn.

Probabilistic model-agnostic meta-learning, in NeurIPS, 2018. C. Finn, K. Xu, and S. Levine.

Gradient-based meta-learning with learned layerwise metric and subspace, in ICML, 2018. Y. Lee and S. Choi.

Recasting gradient-based meta-learning as hierarchical Bayes, in ICLR, 2018. E. Grant, C. Finn, S. Levine, T. Darrell, and T. Griffiths.

Few-shot human motion prediction via meta-learning, in ECCV, 2018. L.-Y. Gui, Y.-X. Wang, D. Ramanan, and J. Moura.

The effects of negative adaptation in model-agnostic meta-learning, arXiv preprint, 2018. T. Deleu and Y. Bengio.

Amortized bayesian meta-learning, in ICLR, 2019. S. Ravi and A. Beatson.

Meta-learning with latent embedding optimization, in ICLR, 2019. A. A. Rusu, D. Rao, J. Sygnowski, O. Vinyals, R. Pascanu, S. Osindero, and R. Hadsell.

参数学习搜索

Optimization as a model for few-shot learning, in ICLR, 2017. S. Ravi and H. Larochelle.

应用场景

计算机视觉

Learning robust visual-semantic embeddings, in CVPR, 2017. Y.-H. Tsai, L.-K. Huang, and R. Salakhutdinov.

Multi-attention network for one shot learning, in CVPR, 2017. P. Wang, L. Liu, C. Shen, Z. Huang, A. van den Hengel, and H. Tao Shen.

One-shot action localization by learning sequence matching network, in CVPR, 2018. H. Yang, X. He, and F. Porikli.

Few-shot and zero-shot multi-label learning for structured label spaces, in EMNLP, 2018. A. Rios and R. Kavuluru.

Meta-dataset: A dataset of datasets for learning to learn from few examples, arXiv preprint, 2019. E. Triantafillou, T. Zhu, V. Dumoulin, P. Lamblin, K. Xu, R. Goroshin, C. Gelada, K. Swersky, P.-A. Manzagol et al.

机器人学

Towards one shot learning by imitation for humanoid robots, in ICRA, 2010. Y. Wu and Y. Demiris.

Learning manipulation actions from a few demonstrations, in ICRA, 2013. N. Abdo, H. Kretzschmar, L. Spinello, and C. Stachniss.

Learning assistive strategies from a few user-robot interactions: Model-based reinforcement learning approach, in ICRA, 2016. M. Hamaya, T. Matsubara, T. Noda, T. Teramae, and J. Morimoto.

One-shot imitation learning, in NeurIPS, 2017. Y. Duan, M. Andrychowicz, B. Stadie, J. Ho, J. Schneider, I. Sutskever, P. Abbeel, and W. Zaremba.

Continuous adaptation via meta-learning in nonstationary and competitive environments, in ICLR, 2018. M. Al-Shedivat, T. Bansal, Y. Burda, I. Sutskever, I. Mordatch, and P. Abbeel.

Deep online learning via meta-learning: Continual adaptation for model-based RL, in ICLR, 2018. A. Nagabandi, C. Finn, and S. Levine.

Meta-learning language-guided policy learning, in ICLR, 2019. J. D. Co-Reyes, A. Gupta, S. Sanjeev, N. Altieri, J. DeNero, P. Abbeel, and S. Levine.

自然语言处理

High-risk learning: Acquiring new word vectors from tiny data, in EMNLP, 2017. A. Herbelot and M. Baroni.

FewRel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation, in EMNLP, 2018. X. Han, H. Zhu, P. Yu, Z. Wang, Y. Yao, Z. Liu, and M. Sun.

声音信号处理

One-shot learning of generative speech concepts, in CogSci, 2014. B. Lake, C.-Y. Lee, J. Glass, and J. Tenenbaum.

Machine speech chain with one-shot speaker adaptation, INTERSPEECH, 2018. A. Tjandra, S. Sakti, and S. Nakamura.

Investigation of using disentangled and interpretable representations for one-shot cross-lingual voice conversion, INTERSPEECH, 2018. S. H. Mohammadi and T. Kim.

其他

A meta-learning perspective on cold-start recommendations for items, in NeurIPS, 2017. M. Vartak, A. Thiagarajan, C. Miranda, J. Bratman, and H. Larochelle.

SMASH: One-shot model architecture search through hypernetworks, in ICLR, 2018. A. Brock, T. Lim, J. Ritchie, and N. Weston.

理论研究相关

Learning to learn around a common mean, in NeurIPS, 2018. G. Denevi, C. Ciliberto, D. Stamos, and M. Pontil.

Meta-learning and universality: Deep representations and gradient descent can approximate any learning algorithm, in ICLR, 2018. C. Finn and S. Levine.