Paper Info
Title
Learning to Self-Train for Semi-Supervised Few-Shot Classification
Abstract
Few-shot classification (FSC) is challenging due to the scarcity of labeled training data (e.g. only one labeled data point per class). Meta-learning has shown to achieve promising results by learning to initialize a classification model for FSC. In this paper we propose a novel semi-supervised meta-learning method called learning to self-train (LST) that leverages unlabeled data and specifically metalearns how to cherry-pick and label such unsupervised data to further improve performance. To this end, we train the LST model through a large number of semi-supervised few-shot tasks. On each task, we train a few-shot model to predict pseudo labels for unlabeled data, and then iterate the self-training steps on labeled and pseudo-labeled data with each step followed by fine-tuning. We additionally learn a soft weighting network (SWN) to optimize the self-training weights of pseudo labels so that better ones can contribute more to gradient descent optimization. We evaluate our LST method on two ImageNet benchmarks for semi-supervised few-shot classification and achieve large improvements over the state-of-the-art method.
Year
Venue
Keywords
2019
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019)
gradient descent optimization
Field
DocType
Volume
Semi-supervised learning,Computer science,Artificial intelligence,Contextual image classification,Machine learning
Conference
32
ISSN
Citations 
PageRank 
1049-5258
4
0.39
References 
Authors
0
7
Name
Order
Citations
PageRank
Xinzhe Li1143.67
Sun Qianru222719.41
Yaoyao Liu3523.88
Qin Zhou4256.82
Shibao Zheng521430.64
Tat-Seng Chua611749653.09
Bernt Schiele712901971.29