RF-Next : Efficient Receptive Field Search for Convolutional Neural Networks
Temporal/spatial receptive fields of models play an important role in sequential/spatial tasks. Large receptive fields facilitate long-term relations, while small receptive fields help to capture the local details. Existing methods construct models with hand-designed receptive fields in layers. Can...
Ausführliche Beschreibung
Bibliographische Detailangaben
Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 3 vom: 17. März, Seite 2984-3002
|
1. Verfasser: |
Gao, Shanghua
(VerfasserIn) |
Weitere Verfasser: |
Li, Zhong-Yu,
Han, Qi,
Cheng, Ming-Ming,
Wang, Liang |
Format: | Online-Aufsatz
|
Sprache: | English |
Veröffentlicht: |
2023
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
Schlagworte: | Journal Article |