A Self-Supervised Deep Learning Framework for Unsupervised Few-Shot Learning and Clustering

By Hongjing Zhang, Tianyang Zhan, Ian N. Davidson. 2021

11 citations recorded by the source corpus.

Abstract The need to learn a good representation is a core problem central to AI. We present a self-supervised representation learning framework and demonstrate its use for few-shot classification and clustering. Our framework can be interpreted as repeatedly discovering new categories from learned embeddings and training a new embedding function with self-supervised signals to differentiate the discovered categories. In our framework, we first discover categories from unlabeled data. Next we post-process the previous partition results to remove outliers and derive prototypes of each category. We then construct few-shot learning tasks with previously selected data and augmented virtual data. Lastly, we iterative train the network through previous steps to learn the final representation. Our framework can considerably outperform previous baselines in unsupervised few-shot classification tasks on miniImageNet and Omniglot data sets. We also validate our learned representation on clustering tasks and demonstrate that our framework further improves upon the recent deep clustering methods.

Subfields: Artificial Intelligence, Ocean Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Ocean Engineering

Citations in the corpus

Novel Class Discovery without Forgetting (2022, background): “Few-shot learning methods [4,57,47] additionally require a few of the unlabeled instances to be labeled.”