DATA : Differentiable ArchiTecture Approximation With Distribution Guided Sampling
Neural architecture search (NAS) is inherently subject to the gap of architectures during searching and validating. To bridge this gap effectively, we develop Differentiable ArchiTecture Approximation (DATA) with Ensemble Gumbel-Softmax (EGS) estimator and Architecture Distribution Constraint (ADC)...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 43(2021), 9 vom: 01. Sept., Seite 2905-2920
|
|---|
| 1. Verfasser: |
Zhang, Xinbang
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Chang, Jianlong,
Guo, Yiwen,
Meng, Gaofeng,
Xiang, Shiming,
Lin, Zhouchen,
Pan, Chunhong |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2021
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |
|---|