1. ZHAW digitalcollection
2. School of Engineering
3. Publikationen
4. Publikationen School of Engineering

Publication type:	Conference paper
Type of review:	Peer review (publication)
Title:	Learning neural models for end-to-end clustering
Authors:	Meier, Benjamin Bruno Elezi, Ismail Amirian, Mohammadreza Dürr, Oliver Stadelmann, Thilo
DOI:	10.21256/zhaw-3850
Proceedings:	Proceedings of the 8th IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR)
Conference details:	8th IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR), Siena, Italy, 19-21 September 2018
Issue Date:	2018
Publisher / Ed. Institution:	IAPR
Language:	English
Subjects:	Perceptual grouping; Learning to cluster; Speech & image clustering
Subject (DDC):	006: Special computer methods
Abstract:	We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters k, and for each 1 <= k <= k_max, a distribution over the individual cluster assignment for each data point. The network is trained in advance in a supervised fashion on separate data to learn grouping by any perceptual similarity criterion based on pairwise labels (same/different group). It can then be applied to different data containing different groups. We demonstrate promising performance on high-dimensional data like images (COIL-100) and speech (TIMIT). We call this “learning to cluster” and show its conceptual difference to deep metric learning, semi-supervise clustering and other related approaches while having the advantage of performing learnable clustering fully end-to-end.
URI:	https://digitalcollection.zhaw.ch/handle/11475/7727
Fulltext version:	Accepted version
License (according to publishing contract):	Not specified
Departement:	School of Engineering
Organisational Unit:	Institute of Applied Information Technology (InIT) Institute of Data Analysis and Process Design (IDP)
Appears in collections:	Publikationen School of Engineering

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.