One-Shot Neural Architecture Search : Maximising Diversity to Overcome Catastrophic Forgetting
One-shot neural architecture search (NAS) has recently become mainstream in the NAS community because it significantly improves computational efficiency through weight sharing. However, the supernet training paradigm in one-shot NAS introduces catastrophic forgetting, where each step of the training...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 43(2021), 9 vom: 04. Sept., Seite 2921-2935
|
|---|
| 1. Verfasser: |
Zhang, Miao
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Li, Huiqi,
Pan, Shirui,
Chang, Xiaojun,
Zhou, Chuan,
Ge, Zongyuan,
Su, Steven |
|---|
| 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
Research Support, U.S. Gov't, Non-P.H.S. |
|---|