Stampnet: unsupervised multi-class object discovery

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

2 Citations (Scopus)


Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background. This is more challenging than image clustering as the size and the location of the objects are not known: this adds additional degrees of freedom and increases the problem complexity. In this work, we propose StampNet, a novel autoencoding neural network that localizes shapes (objects) over a simple background in images and categorizes them simultaneously. StampNet consists of a discrete latent space that is used to categorize objects and to determine the location of the objects. The object categories are formed during the training, resulting in the discovery of a fixed set of objects. We present a set of experiments that demonstrate that StampNet is able to localize and cluster multiple overlapping shapes with varying complexity including the digits from the MNIST dataset. We also present an application of StampNet in the localization of pedestrians in overhead depth-maps.
Original languageEnglish
Title of host publication2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Number of pages5
ISBN (Electronic)978-1-5386-6249-6
Publication statusPublished - Sep 2019
Event26th IEEE International Conference on Image Processing (ICIP 2019) - Taipei, Taiwan, Taipei, Taiwan
Duration: 22 Sep 201925 Sep 2019


Conference26th IEEE International Conference on Image Processing (ICIP 2019)
Abbreviated titleICIP 2019


  • image clustering
  • image localization
  • object discovery
  • unsupervised learning


Dive into the research topics of 'Stampnet: unsupervised multi-class object discovery'. Together they form a unique fingerprint.

Cite this