Learning a Few-shot Embedding Model with Contrastive Learning
AbstractFew-shot learning (FSL) aims to recognize target classes by adapting the prior knowledge learned from source classes. Such knowledge usually resides in a deep embedding model for a general matching purpose of the support and query image pairs. The objective of this paper is to repurpose the contrastive learning for such matching to learn a few-shot embedding model. We make the following contributions: (i) We investigate the contrastive learning with Noise Contrastive Estimation (NCE) in a supervised manner for training a few-shot embedding model; (ii) We propose a novel contrastive training scheme dubbed infoPatch, exploiting the patch-wise relationship to substantially improve the popular infoNCE; (iii) We show that the embedding learned by the proposed infoPatch is more effective; (iv) Our model is thoroughly evaluated on few-shot recognition task; and demonstrates state-of-the-art results on miniImageNet and appealing performance on tieredImageNet, Fewshot-CIFAR100 (FC-100).
How to Cite
Liu, C., Fu, Y., Xu, C., Yang, S., Li, J., Wang, C., & Zhang, L. (2021). Learning a Few-shot Embedding Model with Contrastive Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(10), 8635-8643. https://doi.org/10.1609/aaai.v35i10.17047
AAAI Technical Track on Machine Learning III