자료유형  

 학위논문

Control Number  

0016931146

International Standard Book Number  

9798380367844

Dewey Decimal Classification Number  

621.3

Main Entry-Personal Name  

Yue, Xiangyu.

Publication, Distribution, etc. (Imprint  

[S.l.] : University of California, Berkeley., 2022

Publication, Distribution, etc. (Imprint  

Ann Arbor : ProQuest Dissertations & Theses, 2022

Physical Description  

1 online resource(149 p.)

General Note  

Source: Dissertations Abstracts International, Volume: 85-03, Section: B.

General Note  

Advisor: Sangiovanni-Vincentelli, Alberto.

Dissertation Note  

Thesis (Ph.D.)--University of California, Berkeley, 2022.

Restrictions on Access Note  

This item must not be sold to any third party vendors.

Summary, Etc.  

요약Deep neural networks have achieved great success in learning representations on a given dataset. However, in many cases, the learned representations are dataset-dependent and cannot be transferred to datasets with different distributions, even for the same task. How to deal with domain shift is crucial to improve the generalization capability of models. Domain adaptation offers a potential solution, allowing us to transfer networks from a source domain with abundant labels onto target domains with only limited or no labels.In this dissertation, I will present the many ways that we can learn transferable representations under different scenarios, including 1) when the source domain has only limited labels, even only one label per class, 2) when there are multiple labeled source domains, 3) when there are multiple unseen unlabeled target domains. These approaches are general across different data modalities (e.g. vision and language) and can be easily combined to solve other similar domain transfer settings (e.g. adapting from multiple sources with limited labels), enabling models to generalize beyond the source domains. Many of the works transfer knowledge from simulation data to real-world data in order to alleviate the need for expensive manual annotations. Finally, I present our pioneering work on building a LiDAR point cloud simulator, which has further enabled a large amount of domain adaptation work on LiDAR point cloud segmentation adaptation.

Subject Added Entry-Topical Term  

Electrical engineering.

Subject Added Entry-Topical Term  

Computer science.

Index Term-Uncontrolled  

Domain adaptation

Index Term-Uncontrolled  

Deep neural networks

Index Term-Uncontrolled  

Datasets

Index Term-Uncontrolled  

LiDAR point cloud

Added Entry-Corporate Name  

University of California, Berkeley Electrical Engineering & Computer Sciences

Host Item Entry  

Dissertations Abstracts International. 85-03B.

Host Item Entry  

Dissertation Abstract International

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:639904