FNA++ : Fast Network Adaptation via Parameter Remapping and Architecture Search
Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as the backbone, commonly pre-trained on ImageNet. However, perfo...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 43(2021), 9 vom: 14. Sept., Seite 2990-3004
|
|---|
| 1. Verfasser: |
Fang, Jiemin
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Sun, Yuzhu,
Zhang, Qian,
Peng, Kangjian,
Li, Yuan,
Liu, Wenyu,
Wang, Xinggang |
|---|
| 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 |
|---|