Self-Supervised Learning For Few-Shot Image Classification

14 Nov 2019  ·  Da Chen, Yuefeng Chen, Yuhong Li, Feng Mao, Yuan He, Hui Xue ·

Few-shot image classification aims to classify unseen classes with limited labelled samples. Recent works benefit from the meta-learning process with episodic tasks and can fast adapt to class from training to testing. Due to the limited number of samples for each task, the initial embedding network for meta-learning becomes an essential component and can largely affect the performance in practice. To this end, most of the existing methods highly rely on the efficient embedding network. Due to the limited labelled data, the scale of embedding network is constrained under a supervised learning(SL) manner which becomes a bottleneck of the few-shot learning methods. In this paper, we proposed to train a more generalized embedding network with self-supervised learning (SSL) which can provide robust representation for downstream tasks by learning from the data itself. We evaluate our work by extensive comparisons with previous baseline methods on two few-shot classification datasets ({\em i.e.,} MiniImageNet and CUB) and achieve better performance over baselines. Tests on four datasets in cross-domain few-shot learning classification show that the proposed method achieves state-of-the-art results and further prove the robustness of the proposed model. Our code is available at \hyperref[https://github.com/phecy/SSL-FEW-SHOT.]{https://github.com/phecy/SSL-FEW-SHOT.}

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Few-Shot Image Classification CUB 200 5-way 1-shot AmdimNet Accuracy 77.09 # 19
Few-Shot Image Classification CUB 200 5-way 5-shot AmdimNet Accuracy 89.18 # 16
Few-Shot Image Classification Mini-ImageNet - 1-Shot Learning AmdimNet Accuracy 76.82% # 4
Unsupervised Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) AmdimNet Accuracy 46.13 # 6
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) AmdimNet Accuracy 76.82 # 17
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) AmdimNet Accuracy 90.98 # 6
Unsupervised Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) AmdimNet Accuracy 70.14 # 5

Methods


No methods listed for this paper. Add relevant methods here