Learning to Self-Train for Semi-Supervised Few-Shot Classification

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 meta-learns 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. Code is at https://github.com/xinzheli1217/learning-to-self-train. read more

PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) LST Accuracy 70.1 # 18
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) LST Accuracy 78.7 # 34
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) LST Accuracy 77.7 # 9
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) LST Accuracy 85.2 # 19

Methods


No methods listed for this paper. Add relevant methods here