Back to search

Georgia Institute of Technology

Exploring low-labeled representation learning for learning and perception in realistic scenarios

Abstract

dc:description.abstract

Most progress in computer vision has been on well-curated clean object-centric datasets. This thesis attempts challenging computer vision problems in realistic scenarios. For realism, the following criteria are followed in this work: 1) scene-centric and not object-centric data, and 2) limited or no labeled data. We pick one problem each in learning and perception. Specifically, in the chapter on learning, we: 1) propose Continual Wandering, a novel naturalistic online lifelong learning setting 2) introduce strong baselines suited for this challenging setting and 3) empirically evaluate the baselines and observe a trade-off between online performance and forgetting - methods having good online accuracy also had the highest forgetting. Then we study a case of realistic and low-labeled perception. Specifically, we deal with the problem of 6D pose, size, and estimation. To our knowledge, we are the first to propose an end-to-end method that does detection, localization, and 3D predictions in one forward pass in an in-the-wild setting without using any labeled 3D data. We get impressive qualitative results and comparable quantitative results when compared to baselines.

Degree

thesis:*
Level thesis:degree_level
Masters
Department dc:contributor.department
Computer Science
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Lunayach, Mayank
Advisor dc:contributor.advisor
  • Kira, Zsolt
Committee members dc:contributor.committeemember
  • Hoffman, Judy
  • Vela, Patricio Antonio

Subjects

dc:subject × 10

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/72021

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
related terms
citation

Lunayach, Mayank. Exploring low-labeled representation learning for learning and perception in realistic scenarios. Masters thesis, Georgia Institute of Technology, 2023. https://hdl.handle.net/1853/72021