A Self-Organizing Multiple-View Representations of 3D Objects.

Daphna Weinshall, Shimon Edelman, Heinrich H. Bülthoff

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


We demonstrate the ability of a two-layer network of thresholded summation units to support representation of 3D objects in which several distinct 2D views are stored for ea.ch object. Using unsupervised Hebbian relaxation, the network learned to recognize ten objects from different viewpoints. The training process led to the emergence of compact representations of the specific input views. When tested on novel views of the same objects, the network exhibited a substantial generalization capability. In simulated psychophysical experiments, the network's behavior was qualitatively similar to that of human subjects.
Original languageEnglish
Title of host publicationNIPS 1989
EditorsDavid S. Touretzky
PublisherMorgan Kaufmann Publishers, Inc.
Number of pages8
ISBN (Print)9781558601000
StatePublished - 1989
Event3rd IEEE Conference on Neural Information Processing Systems, NIPS 1989 - Denver, United States
Duration: 27 Nov 198930 Nov 1989
Conference number: 3

Publication series

NameAdvances in neural information processing systems
PublisherMorgan Kaufmann Publishers
ISSN (Print)1049-5258


Conference3rd IEEE Conference on Neural Information Processing Systems, NIPS 1989
Abbreviated titleNIPS 1989
Country/TerritoryUnited States


Dive into the research topics of 'A Self-Organizing Multiple-View Representations of 3D Objects.'. Together they form a unique fingerprint.

Cite this