Skip to main navigation Skip to search Skip to main content

Auto-Encoding Transformations in Reparameterized Lie Groups for Unsupervised Learning

  • Feng Lin
  • , Haohang Xu
  • , Houqiang Li
  • , Hongkai Xiong
  • , Guo Jun Qi*
  • *Corresponding author for this work
  • University of Science and Technology of China
  • Shanghai Jiao Tong University
  • Hefei Comprehensive National Science Center
  • Futurewei Technologies, Inc.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Unsupervised training of deep representations has demonstrated remarkable potentials in mitigating the prohibitive expenses on annotating labeled data recently. Among them is predicting transformations as a pretext task to self-train representations, which has shown great potentials for unsupervised learning. However, existing approaches in this category learn representations by either treating a discrete set of transformations as separate classes, or using the Euclidean distance as the metric to minimize the errors between transformations. None of them has been dedicated to revealing the vital role of the geometry of transformation groups in learning representations. Indeed, an image must continuously transform along the curved manifold of a transformation group rather than through a straight line in the forbidden ambient Euclidean space. This suggests the use of geodesic distance to minimize the errors between the estimated and groundtruth transformations. Particularly, we focus on homographies, a general group of planar transformations containing the Euclidean, similarity and affine transformations as its special cases. To avoid an explicit computing of intractable Riemannian logarithm, we project homographies onto an alternative group of rotation transformations SR(3) with a tractable form of geodesic distance. Experiments demonstrate the proposed approach to Auto-Encoding Transformations exhibits superior performances on a variety of recognition problems.

Original languageEnglish
Title of host publication35th AAAI Conference on Artificial Intelligence, AAAI 2021
PublisherAssociation for the Advancement of Artificial Intelligence
Pages8610-8617
Number of pages8
ISBN (Electronic)9781713835974
DOIs
StatePublished - 2021
Externally publishedYes
Event35th AAAI Conference on Artificial Intelligence, AAAI 2021 - Virtual, Online
Duration: 2 Feb 2021 → 9 Feb 2021

Publication series

Name35th AAAI Conference on Artificial Intelligence, AAAI 2021
Volume10A

Conference

Conference35th AAAI Conference on Artificial Intelligence, AAAI 2021
CityVirtual, Online
Period2/02/21 → 9/02/21

Fingerprint

Dive into the research topics of 'Auto-Encoding Transformations in Reparameterized Lie Groups for Unsupervised Learning'. Together they form a unique fingerprint.

Cite this