Practical Few-Shot Learning

Language: Russian Deep learning now is achieving great results for new tasks, but a the same time modern architecture becomes more and more data and resource hungry. You should collect a huge dataset for achieving an acceptable performance of your model. Few-shot learning technique aims to learn a model to recognize unseen classes during training with limited labeled examples. We want to discuss what few-shot learning is, how to do it right, what kind of problems it can solve and how we use it in our proj