Learning from Few Samples: A Survey

Abstract

Deep neural networks have been able to outperform humans in some cases like image recognition and image classification. However, with the emergence of various novel categories, the ability to continuously widen the learning capability of such networks from limited samples, still remains a challenge. Techniques like Meta-Learning and/or few-shot learning showed promising results, where they can learn or generalize to a novel category/task based on prior knowledge. In this paper, we perform a study of the existing few-shot meta-learning techniques in the computer vision domain based on their method and evaluation metrics. We provide a taxonomy for the techniques and categorize them as data-augmentation, embedding, optimization and semantics based learning for few-shot, one-shot and zero-shot settings. We then describe the seminal work done in each category and discuss their approach towards solving the predicament of learning from few samples. Lastly we provide a comparison of these techniques on the commonly used benchmark datasets: Omniglot, and MiniImagenet, along with a discussion towards the future direction of improving the performance of these techniques towards the final goal of outperforming humans.

17 pages, 10 figures

References in corpus (18)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Sequence to Sequence Learning with Neural Networks
• Natural Language Processing (almost) from Scratch
• How transferable are features in deep neural networks?
• Theoretical Models of Learning to Learn
• Recurrent Models of Visual Attention
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Large-scale Simple Question Answering with Memory Networks
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
• Learning to reinforcement learn
• Billion-scale semi-supervised learning for image classification
• FiLM: Visual Reasoning with a General Conditioning Layer
• Question Answering with Subgraph Embeddings
• Learning to Learn: Meta-Critic Networks for Sample Efficient Learning
• Improving One-Shot Learning through Fusing Side Information
• Discriminative k-shot learning using probabilistic models
• Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey