University of Illinois Urbana-Champaign

Understanding the rich world of outfits: a study of fashion compatibility, latent style, and outfit behavior

Vasileva, Mariya Ivanova

Permalink

https://hdl.handle.net/2142/108720

Description

Title
Understanding the rich world of outfits: a study of fashion compatibility, latent style, and outfit behavior
Author(s)
Vasileva, Mariya Ivanova
Issue Date
2020-07-22
Director of Research (if dissertation) or Advisor (if thesis)
Forsyth, David A
Doctoral Committee Chair(s)
Forsyth, David A
Committee Member(s)
  • Hoiem, Derek
  • Schwing, Alexander
  • Berg, Tamara L
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
  • Computer vision
  • machine learning applications
  • explainability
  • embedding models
  • vision and language
  • image search and retrieval
  • style summarization
  • fashion compatibility
Abstract
Many computer vision applications in the fashion domain require solving tasks where complex relationships between images, such as the notion of item compatibility, are being learned. We take a metric learning approach to representing compatibility between pairs of items. First, we introduce a model that learns compatibility relationships in dedicated embedding subspaces dependent on item type, which results in significant gains on established fashion compatibility prediction tasks. Second, we present a method for learning a richer notion of compatibility across multiple compatibility conditions whose contributions are learned as a latent variable, which provides better performance on established tasks while requiring fewer embedding subspaces to be learned. Third, we make the first published attempt at diagnosing the salient features of a pair of items that make them compatible, and linking them to human-interpretable concepts. Finally, we demonstrate that our representation of outfits enables diverse, novel, and practically-useful visual search queries for the fashion domain, and results in semantically-meaningful style summaries with several directions for future work.
Graduation Semester
2020-08
Type of Resource
Thesis
Permalink
http://hdl.handle.net/2142/108720
Copyright and License Information
Copyright 2020 Mariya I. Vasileva

Owning Collections

Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at Illinois
Dissertations and Theses - Computer Science
Dissertations and Theses from the Dept. of Computer Science