Back to search

Georgia Institute of Technology

Towards Reliable Computer Vision Systems

Abstract

dc:description.abstract

The real world has infinite visual variation – across viewpoints, time, space, and curation. As deep visual models become ubiquitous in high-stakes applications, their ability to generalize across such variation becomes increasingly important. Such generalization will alleviate the need to label a large corpus for every new deployment, which may be infeasible due to data volume (e.g. autonomous driving) or labeling cost (e.g. medical diagnosis). Further, it is necessary to overcome the natural spatiotemporal distribution shifts that a deployed model will invariably face (e.g. changing geographies and seasons). Finally, such generalization will unlock the possibility of knowledge transfer from inexpensive sources of data (e.g. transferring models trained in simulation to reality). In this thesis, I will present opportunities to improve such generalization at different stages of the ML lifecycle. First, I will discuss proactive strategies for training robust models by leveraging simulation to augment the long tail of real training data. Next, I will present reactive strategies to recover from unforeseen distribution shifts via self-supervised domain adaptation. Finally, I will present a framework to stress-test the robustness of vision models by leveraging foundation models for text and image synthesis to generate challenging counterfactual test cases.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Interactive Computing
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Prabhu, Viraj Uday
Advisor dc:contributor.advisor
  • Hoffman, Judy
Committee members dc:contributor.committeemember
  • Batra, Dhruv
  • Fidler, Sanja
  • Hays, James
  • Kira, Zsolt

Subjects

dc:subject × 3

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/75198

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Prabhu, Viraj Uday. Towards Reliable Computer Vision Systems. Doctoral thesis, Georgia Institute of Technology, 2024. https://hdl.handle.net/1853/75198