A Patch-as-Filter Method for Same-Different Problems with Few-Shot Learning

Convolutional Neural Network (CNN) has undergone tremendous advancements in recent years, but visual reasoning tasks are still a huge undertaking, particularly in few-shot learning cases. Little is known, especially in solving the Same-Different (SD) task, which is a type of visual reasoning task that requires seeking pattern repetitions in a single image. In this thesis, we propose a patch-as-filter method focusing on solving the SD tasks with few-shot learning. Firstly, a patch in an individual image is detected. Then, transformations are learned to create sample-specific convolutional filters. After applying these filters on the original input images, we, lastly, acquire feature maps indicating the duplicate segments. We show experimentally that our approach achieves the state-of-the-art few-shot performance on the Synthetic Visual Reasoning Test (SVRT) SD tasks by accuracy going up above 30% on average, with only ten training samples. Besides that, to further evaluate the effectiveness of our approach, SVRT-like tasks are generated with more difficult visual reasoning concepts. The results suggest that the average accuracy is increased by approximately 10% compared to several popular few-shot algorithms. The method we suggest here has shed new light upon new CNN approaches in solving the SD tasks with few-shot learning.

Name thesis:degree_name

M Sc

Discipline thesis:degree_discipline

Computer Science

Grantor dc:publisher

The University of Western Ontario

Year dc:date.issued

2020

Author dc:creator

• Hu, Yining

Advisor dc:contributor.advisor

• Ling, Charles

• Visual reasoning
• Few-shot learning
• Dynamic filters
• Convolutional Neural Network

Language dc:language.iso

en_ca

Handle dc:identifier.uri

https://hdl.handle.net/20.500.14721/30050

OAI identifier oai:identifier

oai:uwo.scholaris.ca:20.500.14721/30050