REPRESENTATIVE PROTOTYPE WITH CONSTRASTIVE LEARNING FOR SEMI-SUPENVISED FEW-SHOT CLASSIFICATION

Hexiu Lin, Daming Shi, Yukun Liu

Keywords: SEMI-SUPENVISED FEW-SHOT CLASSIFICATION

Abstract: Few-shot learning aims to learn novel classes in the dataset with few samples per class, which is a very challenging task. To mitigate this issue, the prior work obtain representative prototypes with semantic embeddin based on prototypical networks. While the above methods do not meet the requirement of few-shot learning, which requires abundant labeled samples. Therefore, We propose a new model framework to get representative prototypes with semi-supervised learning. Specifically, we introduces the dataset containing unlabeled samples to assist training the model. More importantly, to fully utilize these unlabeled samples, we adopt conditional variational autoencoder to construct more representative prototypes. Simultaneously, we develop novel contrastive loss to improve the model generalization ability. We evaluate our method on miniImageNet and tieredImageNet benchmarks for both 1-shot and 5-shot settings and achieve better performance over the state-of-the-art semisupervised few-shot method.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning