Few Shot Learning With No Labels
arXiv:2012.13751
Abstract
Few-shot learners aim to recognize new categories given only a small number of training samples. The core challenge is to avoid overfitting to the limited data while ensuring good generalization to novel classes. Existing literature makes use of vast amounts of annotated data by simply shifting the label requirement from novel classes to base classes. Since data annotation is time-consuming and costly, reducing the label requirement even further is an important goal. To that end, our paper presents a more challenging few-shot setting where no label access is allowed during training or testing. By leveraging self-supervision for learning image representations and image similarity for classification at test time, we achieve competitive baselines while using \textbf{zero} labels, which is at least fewer labels than state-of-the-art. We hope that this work is a step towards developing few-shot learning methods which do not depend on annotated data at all. Our code will be publicly released.
References in corpus (12)
- A Simple Framework for Contrastive Learning of Visual Representations
- Prototypical Networks for Few-shot Learning
- Improved Baselines with Momentum Contrastive Learning
- A Survey on Multi-Task Learning
- Contrastive Multiview Coding
- Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
- One-Shot Unsupervised Cross Domain Translation
- Alpha MAML: Adaptive Model-Agnostic Meta-Learning
- Improving One-Shot Learning through Fusing Side Information
- Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
- Self-Supervised Learning For Few-Shot Image Classification
- Efficient K-Shot Learning with Regularized Deep Networks