Semi-Supervised and Active Few-Shot Learning with Prototypical Networks

We consider the problem of semi-supervised few-shot classification where a classifier needs to adapt to new tasks using a few labeled examples and (potentially many) unlabeled examples. We propose a clustering approach to the problem. The features extracted with Prototypical Networks are clustered using $K$-means with the few labeled examples guiding the clustering process. We note that in many real-world applications the adaptation performance can be significantly improved by requesting the few labels through user feedback. We demonstrate good performance of the active adaptation strategy using image data.

[1]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .

[2]  Shin Ishii,et al.  Distributional Smoothing with Virtual Adversarial Training , 2015, ICLR 2016.

[3]  Raquel Urtasun,et al.  Deep Spectral Clustering Learning , 2017, ICML.

[4]  Stefanie Jegelka,et al.  Deep Metric Learning via Facility Location , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[6]  Silvio Savarese,et al.  Deep Metric Learning via Lifted Structured Feature Embedding , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[10]  Geoffrey E. Hinton,et al.  Matrix capsules with EM routing , 2018, ICLR.

[11]  Arindam Banerjee,et al.  Semi-supervised Clustering by Seeding , 2002, ICML.

[12]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

[13]  Ambedkar Dukkipati,et al.  Attentive Recurrent Comparators , 2017, ICML.

[14]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[15]  Andrew McCallum,et al.  Semi-Supervised Clustering with User Feedback , 2003 .

[16]  Sergey Levine,et al.  One-Shot Visual Imitation Learning via Meta-Learning , 2017, CoRL.

[17]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[18]  Joshua B. Tenenbaum,et al.  Meta-Learning for Semi-Supervised Few-Shot Classification , 2018, ICLR.

[19]  Claire Cardie,et al.  Proceedings of the Eighteenth International Conference on Machine Learning, 2001, p. 577–584. Constrained K-means Clustering with Background Knowledge , 2022 .

[20]  Harri Valpola,et al.  Weight-averaged consistency targets improve semi-supervised deep learning results , 2017, ArXiv.

[21]  Xiaojin Zhu,et al.  Semi-Supervised Learning , 2010, Encyclopedia of Machine Learning.

[22]  Stefan Wrobel,et al.  Active Hidden Markov Models for Information Extraction , 2001, IDA.

[23]  Tapani Raiko,et al.  Semi-supervised Learning with Ladder Networks , 2015, NIPS.

[24]  Timo Aila,et al.  Temporal Ensembling for Semi-Supervised Learning , 2016, ICLR.

[25]  Hang Li,et al.  Meta-SGD: Learning to Learn Quickly for Few Shot Learning , 2017, ArXiv.

[26]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[27]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

[28]  Hong Yu,et al.  Meta Networks , 2017, ICML.