Class-Based Variational Representation Learning For Robust Image Retrieval

Nikolaos Passalis, Anastasios Tefas, Alexandros Iosifidis, Moncef Gabbouj

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

1 Citation (Scopus)


Supervised learning for Content-based Information Retrieval allows for obtaining discriminative representations that often excel within the training domain. However, recent evidence suggests that these representations can actually harm the retrieval precision for queries that do not belong to the domain of the training set compared to other, less discriminative representations. To avoid this behavior, we propose to learn discriminative representations which also encode the latent generative factors for each class. In this way, the proposed method is capable of maintaining (part of) the in-class variance, as well as being able to represent data that belong to classes that were not seen during the training by better learning the structure of the input space. The proposed method is evaluated under different in-domain and out-of-domain setups, significantly outperforming existing supervised and unsupervised representation learning approaches.
Original languageEnglish
Title of host publication2019 IEEE International Conference on Image Processing (ICIP)
Number of pages5
ISBN (Electronic)978-1-5386-6249-6
ISBN (Print)978-1-5386-6250-2
Publication statusPublished - Sept 2019
Publication typeA4 Article in conference proceedings
EventIEEE International Conference on Image Processing -
Duration: 1 Jan 1900 → …

Publication series

NameIEEE International Conference on Image Processing
ISSN (Print)1522-4880
ISSN (Electronic)2381-8549


ConferenceIEEE International Conference on Image Processing
Period1/01/00 → …


  • Training
  • Task analysis
  • Feature extraction
  • Image retrieval
  • Image reconstruction
  • Optimization
  • Data mining
  • Image Retrieval
  • Supervised Representation Learning
  • Metric Learning

Publication forum classification

  • Publication forum level 1


Dive into the research topics of 'Class-Based Variational Representation Learning For Robust Image Retrieval'. Together they form a unique fingerprint.

Cite this