MIGO-NAS : Towards Fast and Generalizable Neural Architecture Search
Neural architecture search (NAS) has achieved unprecedented performance in various computer vision tasks. However, most existing NAS methods are defected in search efficiency and model generalizability. In this paper, we propose a novel NAS framework, termed MIGO-NAS, with the aim to guarantee the e...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 43(2021), 9 vom: 03. Sept., Seite 2936-2952
|
|---|
| 1. Verfasser: |
Zheng, Xiawu
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Ji, Rongrong,
Chen, Yuhang,
Wang, Qiang,
Zhang, Baochang,
Chen, Jie,
Ye, Qixiang,
Huang, Feiyue,
Tian, Yonghong |
|---|
| 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 |
|---|