MSc THESIS PRESENTATION : Yuanyuan Han

Supervisor: Dr. Charles Ling

Thesis Examiners: Dr. Mike Bauer Dr. Dan Lizotte

Extra-Departmental Examiner: Dr. Xiaoming Liu

A New Method to Solve Same-different Problems with Few-shot Learning

Visual learning of highly abstract concepts is often simple for humans but very challenging for machines. Same-different (SD) problems are a visual reasoning task with highly abstract concepts. Previous work has shown that SD problems are difficult to solve with standard deep learning algorithms, especially in the few-shot case, despite the ability of such algorithms to learn abstract features. In this thesis, we propose a new method to solve SD problems with few training samples, in which same-different visual concepts can be recognized by examining similarities between Regions of Interest by using a same-different twins network. Our method achieves state-of-the-art results on the Synthetic Visual Reasoning Test SD tasks and outperforms several strong baselines, achieving accuracy above 95% on several tasks and above 85% on average with only 10 training samples. On a few of these challenging SD tasks, our approach even outperforms reported human performance. We further evaluate the performance of our method outside of the synthetic tasks and achieve good performance on the MNIST, FashionMNIST and Face Recognition datasets.