Back to Search
Start Over
Learning Neural Models for End-to-End Clustering
- Source :
- Artificial Neural Networks in Pattern Recognition ISBN: 9783319999777, ANNPR
- Publication Year :
- 2018
- Publisher :
- arXiv, 2018.
-
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 $1 \leq k \leq k_\mathrm{max}$, 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.<br />Comment: Accepted for publication on ANNPR 2018
- Subjects :
- Computer Science::Machine Learning
FOS: Computer and information sciences
Computer Science - Machine Learning
Computer Science - Artificial Intelligence
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
TIMIT
Machine Learning (stat.ML)
02 engineering and technology
Learning to cluster
006: Spezielle Computerverfahren
Machine Learning (cs.LG)
End-to-end principle
Statistics - Machine Learning
0202 electrical engineering, electronic engineering, information engineering
Cluster (physics)
Point (geometry)
Cluster analysis
Group (mathematics)
business.industry
020207 software engineering
Pattern recognition
Speech & image clustering
ComputingMethodologies_PATTERNRECOGNITION
Artificial Intelligence (cs.AI)
Metric (mathematics)
020201 artificial intelligence & image processing
Pairwise comparison
Artificial intelligence
business
Perceptual grouping
Subjects
Details
- ISBN :
- 978-3-319-99977-7
- ISBNs :
- 9783319999777
- Database :
- OpenAIRE
- Journal :
- Artificial Neural Networks in Pattern Recognition ISBN: 9783319999777, ANNPR
- Accession number :
- edsair.doi.dedup.....d487386d18753cd5f1a9b94705312da7
- Full Text :
- https://doi.org/10.48550/arxiv.1807.04001