Traditional deep learning has allowed us to learn unstructured features using large labeled training set. However, deep learning runs into various issues, when there is lack of large dataset. Few-Shot Learning (FSL) can be used to solve this problem. This methodology has gained popularity because it helps in making predictions using a limited number of examples with supervised information, that is with few training samples. There are different techniques under FSL. In this session, our speaker will be be focusing on FSL in computer vision, and how it breaks standard ML paradigms.