Boosting Few-Shot Visual Learning with Self-Supervision
This work addresses the challenge of training models with limited labeled data for visual recognition, offering an incremental improvement by combining existing few-shot and self-supervised learning methods.
The paper tackles the problem of few-shot visual learning by integrating self-supervision as an auxiliary task to enhance feature representations, resulting in consistent improvements across various architectures, datasets, and self-supervision techniques.
Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to recognize patterns in the low data regime. Self-supervised learning focuses instead on unlabeled data and looks into it for the supervisory signal to feed high capacity deep neural networks. In this work we exploit the complementarity of these two domains and propose an approach for improving few-shot learning through self-supervision. We use self-supervision as an auxiliary task in a few-shot learning pipeline, enabling feature extractors to learn richer and more transferable visual representations while still using few annotated samples. Through self-supervision, our approach can be naturally extended towards using diverse unlabeled data from other datasets in the few-shot setting. We report consistent improvements across an array of architectures, datasets and self-supervision techniques.