Stampnet: unsupervised multi-class object discovery

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

1 Citaat (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.
Originele taal-2Engels
Titel2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers
Aantal pagina's5
ISBN van elektronische versie978-1-5386-6249-6
StatusGepubliceerd - sep 2019
Evenement2019 IEEE International Conference on Image Processing (ICIP) - Taipei, Taiwan
Duur: 22 sep 201925 sep 2019


Congres2019 IEEE International Conference on Image Processing (ICIP)

Vingerafdruk Duik in de onderzoeksthema's van 'Stampnet: unsupervised multi-class object discovery'. Samen vormen ze een unieke vingerafdruk.

Citeer dit