Prototypical networks for few-shot learning. Snell, J., Swersky, K., & Zemel, R. In Proceedings of the 31st International Conference on Neural Information Processing Systems, of NIPS'17, pages 4080–4090, Red Hook, NY, USA, December, 2017. Curran Associates Inc.. abstract bibtex We propose Prototypical Networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical Networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend Prototypical Networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.
@inproceedings{snell_prototypical_2017,
address = {Red Hook, NY, USA},
series = {{NIPS}'17},
title = {Prototypical networks for few-shot learning},
isbn = {978-1-5108-6096-4},
abstract = {We propose Prototypical Networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical Networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend Prototypical Networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.},
language = {en},
urldate = {2023-07-05},
booktitle = {Proceedings of the 31st {International} {Conference} on {Neural} {Information} {Processing} {Systems}},
publisher = {Curran Associates Inc.},
author = {Snell, Jake and Swersky, Kevin and Zemel, Richard},
month = dec,
year = {2017},
keywords = {\#Few-shot, \#NIPS{\textgreater}17, \#⭐⭐⭐⭐⭐, /readed, ❤️, ⭐⭐⭐⭐⭐},
pages = {4080--4090},
}
Downloads: 0
{"_id":"EE4HDvymrjsm4bNWL","bibbaseid":"snell-swersky-zemel-prototypicalnetworksforfewshotlearning-2017","authorIDs":[],"author_short":["Snell, J.","Swersky, K.","Zemel, R."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Red Hook, NY, USA","series":"NIPS'17","title":"Prototypical networks for few-shot learning","isbn":"978-1-5108-6096-4","abstract":"We propose Prototypical Networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical Networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend Prototypical Networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.","language":"en","urldate":"2023-07-05","booktitle":"Proceedings of the 31st International Conference on Neural Information Processing Systems","publisher":"Curran Associates Inc.","author":[{"propositions":[],"lastnames":["Snell"],"firstnames":["Jake"],"suffixes":[]},{"propositions":[],"lastnames":["Swersky"],"firstnames":["Kevin"],"suffixes":[]},{"propositions":[],"lastnames":["Zemel"],"firstnames":["Richard"],"suffixes":[]}],"month":"December","year":"2017","keywords":"#Few-shot, #NIPS\\textgreater17, #⭐⭐⭐⭐⭐, /readed, ❤️, ⭐⭐⭐⭐⭐","pages":"4080–4090","bibtex":"@inproceedings{snell_prototypical_2017,\n\taddress = {Red Hook, NY, USA},\n\tseries = {{NIPS}'17},\n\ttitle = {Prototypical networks for few-shot learning},\n\tisbn = {978-1-5108-6096-4},\n\tabstract = {We propose Prototypical Networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical Networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend Prototypical Networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.},\n\tlanguage = {en},\n\turldate = {2023-07-05},\n\tbooktitle = {Proceedings of the 31st {International} {Conference} on {Neural} {Information} {Processing} {Systems}},\n\tpublisher = {Curran Associates Inc.},\n\tauthor = {Snell, Jake and Swersky, Kevin and Zemel, Richard},\n\tmonth = dec,\n\tyear = {2017},\n\tkeywords = {\\#Few-shot, \\#NIPS{\\textgreater}17, \\#⭐⭐⭐⭐⭐, /readed, ❤️, ⭐⭐⭐⭐⭐},\n\tpages = {4080--4090},\n}\n\n\n\n","author_short":["Snell, J.","Swersky, K.","Zemel, R."],"key":"snell_prototypical_2017-1","id":"snell_prototypical_2017-1","bibbaseid":"snell-swersky-zemel-prototypicalnetworksforfewshotlearning-2017","role":"author","urls":{},"keyword":["#Few-shot","#NIPS\\textgreater17","#⭐⭐⭐⭐⭐","/readed","❤️","⭐⭐⭐⭐⭐"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/zzhenry2012","creationDate":"2020-02-11T20:02:58.217Z","downloads":0,"keywords":["#few-shot","#nips\\textgreater17","#⭐⭐⭐⭐⭐","/readed","❤️","⭐⭐⭐⭐⭐"],"search_terms":["prototypical","networks","few","shot","learning","snell","swersky","zemel"],"title":"Prototypical networks for few-shot learning","year":2017,"dataSources":["9ZC4Jom7ygp8s9git","iwKepCrWBps7ojhDx","nZHrFJKyxKKDaWYM8"]}