Back to search

Cornell University

Lowshot Segmentation

Abstract

dc:description.abstract

Learning from limited supervision has become an area of interest in machine learning because deep learning systems have demonstrated a dependence on large, labeled data sets which can be costly and sometimes unfeasible to obtain. A subset of this endeavor is the task of low-shot learning which is learning from a handful of labeled examples and has seen recent attention in image recognition. In this work we investigate the low-shot learning paradigm in the context of semantic segmentation, the challenges that it presents, and develop techniques for addressing these challenges. We first explore multiple ways in which limited labeling can occur in the task of semantic segmentation which is not a straight forward extension of its image recognition counter-part. Next we present novel techniques for increasing performance which include a form of learned data augmentation and incorporating inductive biases about local context to leverage unlabeled data. Finally we shift the experiments to a more natural and general setting in which the data naturally follows a heavy-tail distribution over the class frequency and size rather than artificially limiting labeled data for certain classes.

Degree

thesis:*
Name thesis:degree_name
M.S., Computer Science
Level thesis:degree_level
Master of Science
Discipline thesis:degree_discipline
Computer Science
Grantor
Cornell University
Year dc:date.issued
2019

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Wallingford, Matthew C
Chair dc:contributor.chair
  • Hariharan, Bharath
Committee member dc:contributor.committeemember
  • Sridharan, Karthik

Subjects

dc:subject × 7

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Dc Identifier Bibid
11050386
Dc Identifier Other
ProQuest Submission ID: 10550
ProQuest Publication ID: 13883710

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Wallingford, Matthew C. Lowshot Segmentation. Master of Science thesis, Cornell University, 2019. https://hdl.handle.net/1813/67404