ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2303.05102
26
0

StyleDiff: Attribute Comparison Between Unlabeled Datasets in Latent Disentangled Space

9 March 2023
Keisuke Kawano
Takuro Kutsuna
Ryoko Tokuhisa
Akihiro Nakamura
Yasushi Esaki
ArXivPDFHTML
Abstract

One major challenge in machine learning applications is coping with mismatches between the datasets used in the development and those obtained in real-world applications. These mismatches may lead to inaccurate predictions and errors, resulting in poor product quality and unreliable systems. In this study, we propose StyleDiff to inform developers of the differences between the two datasets for the steady development of machine learning systems. Using disentangled image spaces obtained from recently proposed generative models, StyleDiff compares the two datasets by focusing on attributes in the images and provides an easy-to-understand analysis of the differences between the datasets. The proposed StyleDiff performs in O(dNlog⁡N)O (d N\log N)O(dNlogN), where NNN is the size of the datasets and ddd is the number of attributes, enabling the application to large datasets. We demonstrate that StyleDiff accurately detects differences between datasets and presents them in an understandable format using, for example, driving scenes datasets.

View on arXiv
Comments on this paper