Prototypical Networks for Few-shot Learning

Jake Snell, Kevin Swersky, Richard S. Zemel · Neural Information Processing Systems · 2017

Summary

This work proposes Prototypical Networks for few-shot classification, and provides an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning.

Type: preprint
Published: 2017-03-15
Cited by: 10,440
References: 39
Access: Open access
DOI: https://doi.org/10.48550/arxiv.1703.05175
arXiv: https://arxiv.org/abs/1703.05175
OpenAlex: https://openalex.org/W2601450892
Semantic Scholar: https://api.semanticscholar.org/CorpusID:309759

Keywords

Shot (pellet), Business, Computer science, Materials science

References

Caltech-UCSD Birds 200Peter Welinder, Steve Branson, Mita, Takeshi — 2010
Learning a Nonlinear Embedding by Preserving Class Neighbourhood StructureRuslan Salakhutdinov, Geoffrey E. Hinton — 2007
Very Deep Convolutional Networks for Large-Scale Image RecognitionKaren Simonyan, Andrew Zisserman — 2014
Stochastic Backpropagation and Approximate Inference in Deep Generative ModelsDanilo Jimenez Rezende, Shakir Mohamed, Daan Wierstra — 2014
A Survey on Metric Learning for Feature Vectors and Structured DataAurélien Bellet, Amaury Habrard, Marc Sebban — 2013
Auto-Encoding Variational BayesDiederik P. Kingma, Max Welling — 2013
Distance-Based Image Classification: Generalizing to New Classes at Near-Zero CostThomas Mensink, Jakob Verbeek, Florent Perronnin — 2013
Evaluation of output embeddings for fine-grained image classificationZeynep Akata, Scott Reed, Daniel Walter — 2014
Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber — 1997
Clustering with Bregman DivergencesArindam Banerjee, Srujana Merugu, Inderjit S. Dhillon — 2005
Going deeper with convolutionsChristian Szegedy, Wei Liu, Yangqing Jia — 2014
Distance Metric Learning for Large Margin Nearest Neighbor ClassificationKilian Q. Weinberger, Lawrence K. Saul — 2005
Label-Embedding for Attribute-Based ClassificationZeynep Akata, Florent Perronnin, Zaïd Harchaoui — 2013
ImageNet Large Scale Visual Recognition ChallengeOlga Russakovsky, Jia Deng, Hao Su — 2014
Metric Learning: A SurveyBrian Kulis — 2013
Learning from one example through shared densities on transformsMarion G. Miller, Nicholas E. Matsakis, Paul Viola — 2000
A Deep Non-linear Feature Mapping for Large-Margin kNN ClassificationRenqiang Min, David A. Stanley, Zineng Yuan — 2009
Neighbourhood Components AnalysisJacob Goldberger, Geoffrey E. Hinton, Sam T. Roweis — 2004
Write a Classifier: Zero-Shot Learning Using Purely Textual DescriptionsMohamed Elhoseiny, Babak Saleh, Ahmed Elgammal — 2013
ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton — 2012

Cited by

Towards Partial Supervision for Generic Object Counting in Natural Scenesまゆみ佐藤, 律子大室, 敬子根本 — 2019
Deep Reinforcement Learning: An OverviewYuxi Li — 2017
Generative Adversarial Residual Pairwise Networks for One Shot LearningAkshay Mehrotra, Ambedkar Dukkipati — 2017
Discriminative k-shot learning using probabilistic modelsMatthias Bauer, Mateo Rojas-Carulla, Jakub Świątkowski — 2017
Labeled Memory Networks for Online Model AdaptationShiv Shankar, Sunita Sarawagi — 2017
Transfer Learning for Cross-Dataset Recognition: A SurveyJing Zhang, Wanqing Li, Philip Ogunbona — 2017
A Simple Neural Attentive Meta-LearnerNikhil Mishra, Mostafa Rohaninejad, Xi Chen — 2017
Engineering Applications of Artificial IntelligenceChakir, Aziza, Andry, Johanes Fernandes, Ullah, Arif — 2024
Gaussian Prototypical Networks for Few-Shot Learning on OmniglotStanislav Fort — 2017
Learning to Model the TailYu-Xiong Wang, Deva Ramanan, Martial Hebert — 2017
A Meta-Learning Perspective on Cold-Start Recommendations for ItemsManasi Vartak, Arvind Thiagarajan, Conrado Silva Miranda — 2017
How intelligent are convolutional neural networks?Zhennan Yan, Xiang Sean Zhou — 2017
Deep Learning for Case-based Reasoning through Prototypes: A Neural Network that Explains its PredictionsOscar Li, Hao Liu, Chaofan Chen — 2017
Prototype Matching Networks for Large-Scale Multi-label Genomic Sequence ClassificationJack Lanchantin, Arshdeep Sekhon, Ritambhara Singh — 2017
Learning to Learn Image Classifiers with Informative Visual AnalogyLinjun Zhou, Peng Cui, Shiqiang Yang — 2017
Improving One-Shot Learning through Fusing Side InformationYao-Hung Hubert Tsai, Ruslan Salakhutdinov — 2017
Learning with Latent LanguageJacob Andreas, Dan Klein, Sergey Levine — 2017
Discovering Order in Unordered Datasets: Generative Markov NetworksYao-Hung Hubert Tsai, Han Zhao, Nebojša Jojić — 2017
Learning to Compare: Relation Network for Few-Shot LearningFlood Sung, Yongxin Yang, Li Zhang — 2017
Siamese Networks for Chromosome ClassificationSwati, Gaurav Gupta, Mohit Yadav — 2017

Prototypical Networks for Few-shot Learning

Summary

Keywords

References

Cited by

Related papers