Self-Supervised Latent Space Optimization With Nebula Variational Coding

Deep learning approaches process data in a layer-by-layer way with intermediate (or latent) features. We aim at designing a general solution to optimize the latent manifolds to improve the performance on classification, segmentation, completion and/or reconstruction through probabilistic models. Thi...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 46(2024), 3 vom: 10. Feb., Seite 1397-1411
1. Verfasser: Wang, Yida (VerfasserIn)
Weitere Verfasser: Tan, David Joseph, Navab, Nassir, Tombari, Federico
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000caa a22002652 4500
001 NLM338465847
003 DE-627
005 20240207231944.0
007 cr uuu---uuuuu
008 231226s2024 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2022.3160539  |2 doi 
028 5 2 |a pubmed24n1283.xml 
035 |a (DE-627)NLM338465847 
035 |a (NLM)35316182 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Wang, Yida  |e verfasserin  |4 aut 
245 1 0 |a Self-Supervised Latent Space Optimization With Nebula Variational Coding 
264 1 |c 2024 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 07.02.2024 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Deep learning approaches process data in a layer-by-layer way with intermediate (or latent) features. We aim at designing a general solution to optimize the latent manifolds to improve the performance on classification, segmentation, completion and/or reconstruction through probabilistic models. This paper proposes a variational inference model which leads to a clustered embedding. We introduce additional variables in the latent space, called nebula anchors, that guide the latent variables to form clusters during training. To prevent the anchors from clustering among themselves, we employ the variational constraint that enforces the latent features within an anchor to form a Gaussian distribution, resulting in a generative model we refer as Nebula Variational Coding (NVC). Since each latent feature can be labeled with the closest anchor, we also propose to apply metric learning in a self-supervised way to make the separation between clusters more explicit. As a consequence, the latent variables of our variational coder form clusters which adapt to the generated semantic of the training data, e.g., the categorical labels of each sample. We demonstrate experimentally that it can be used within different architectures designed to solve different problems including text sequence, images, 3D point clouds and volumetric data, validating the advantage of our proposed method 
650 4 |a Journal Article 
700 1 |a Tan, David Joseph  |e verfasserin  |4 aut 
700 1 |a Navab, Nassir  |e verfasserin  |4 aut 
700 1 |a Tombari, Federico  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 46(2024), 3 vom: 10. Feb., Seite 1397-1411  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:46  |g year:2024  |g number:3  |g day:10  |g month:02  |g pages:1397-1411 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2022.3160539  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 46  |j 2024  |e 3  |b 10  |c 02  |h 1397-1411