Improving few-shot object detection by saving and hallucinating examples

Learning to detect an object in an image from very few training examples - few-shot object detection - is challenging, because the classifier that sees proposal boxes has very little training data. A particularly challenging training regime occurs when there are one or two training examples. In this case, if the region proposal network (RPN) misses even one high intersection-over-union (IOU) training box, the classifier's model of how object appearance varies can be severely impacted. We use multiple distinct yet cooperating RPN's. Our RPN's are trained to be different, but not too different; doing so yields significant performance improvements over state of the art for COCO and PASCAL VOC in the very few-shot setting. This effect appears to be independent of the choice of classifier or dataset. However, under the very low-shot regime, even if all high IOU boxes are used to train the classifier, the variations are still insufficient to train the classifier in novel classes. We propose to build an even better model of variation in novel classes by transferring the shared within-class variation from base classes. We introduce a hallucinator network and insert it into a modern object detector model, which learns to generate additional training examples in the Region of Interest (ROI's) feature space. This approach yields further performance improvements on two state-of-the-art few-shot detectors with different proposal generation processes.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2021

Author dc:creator

• Zhang, Weilin

Contributors dc:contributor

• Forsyth, David Alexander

• Object Detection
• Few-Shot Learning

Statement dc:rights

• Copyright 2020 Weilin Zhang

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/109535

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/109535