Learning neural models for end-to-end clustering
- 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≤kmax, 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.
Download full text files
Accepted Version
Additional Services
Statistics
| Author: | Benjamin Bruno Meier, Ismail Elezi, Mohammadreza Amirian, Oliver DürrORCiDGND, Thilo Stadelmann |
|---|---|
| URN: | urn:nbn:de:bsz:kon4-opus4-22863 |
| DOI: | https://doi.org/10.1007/978-3-319-99978-4_10 |
| ISBN: | 978-3-319-99977-7 |
| ISBN: | 978-3-319-99978-4 |
| Parent Title (English): | 8th IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR), 19-21 September 2018, Siena, Italy |
| Publisher: | Springer |
| Place of publication: | Cham |
| Document Type: | Conference Proceeding |
| Language: | English |
| Year of Publication: | 2018 |
| Release Date: | 2020/01/21 |
| Tag: | Perceptual grouping; Learning to cluster; Speech & image clustering |
| Edition: | Akzeptierte Version |
| First Page: | 126 |
| Last Page: | 138 |
| Institutes: | Institut für Optische Systeme - IOS |
| DDC functional group: | 006 Spezielle Computerverfahren |
| Open Access?: | Ja |
| Licence (German): |  Urheberrechtlich geschützt |
