Sample-efficient learning with self-supervision

Sample efficiency is a crucial aspect of machine learning algorithms. A more sample-efficient algorithm can achieve better performance with less training data. On the other hand, the success of modern machine learning relies heavily on large data samples. For example, a visual recognition system typically needs to be trained on thousands or millions of labeled images to reach good accuracy. In addition, a reinforcement learning agent needs to experience a vast number of environmental interactions to be competitive. With the ever-growing demand for real-world machine learning solutions, it becomes imperative to develop more sample-efficient algorithms that rely less on human annotations or environment interactions and thus can learn more efficiently. Learning from self-supervision has recently emerged as a promising way to improve sample efficiency. The idea is that we can train the model with supervision signals generated not by human annotators or the environment but rather by the carefully constructed self-supervised tasks based on the model itself. In this dissertation, I present my contributions to improving the sample efficiency of machine learning with self-supervision for visual and reinforcement learning problems. The dissertation naturally breaks down into three parts according to the techniques used. The first two parts contain methods designed for vision tasks such as object detection and image segmentation. The core idea is either to leverage pseudo labels generated by an existing model, as in Chapters 2-3, or to leverage the invariance and equivariance property that we know to be inherently true for natural images, as in Chapters 4-6. The third part describes my research projects on building more sample-efficient reinforcement learning algorithms based on the ideas of self-supervised video prediction, self-play against a population, and self-critic with variance reduction as in Chapters 7-9. Altogether, this dissertation demonstrates multiple effective ways to improve the sample efficiency of machine learning across a wide range of tasks and the tremendous potential of self-supervision in the development of future AI systems.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2022

Author dc:creator

• Zhong, Yuanyi

Contributors dc:contributor

• Wang, Yuxiong
• Peng, Jian
• Forsyth, David
• Zhang, Lei

• Deep Learning
• Self-supervised Learning
• Computer Vision
• Reinforcement Learning
• Sample Efficiency
• Artificial Intelligence

Statement dc:rights

• Copyright 2022 Yuanyi Zhong

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/117813

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F117813