Mutual Information Regularized Feature-Level Frankenstein for Discriminative Recognition
Deep learning recognition approaches can potentially perform better if we can extract a discriminative representation that controllably separates nuisance factors. In this paper, we propose a novel approach to explicitly enforce the extracted discriminative representation d, extracted latent variati...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 9 vom: 04. Sept., Seite 5243-5260
|
|---|
| 1. Verfasser: |
Liu, Xiaofeng
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Yang, Chao,
You, Jane,
Kuo, C-C Jay,
Kumar, B V K Vijaya |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |
|---|