Spatially Adaptive Feature Refinement for Efficient Inference
Spatial redundancy commonly exists in the learned representations of convolutional neural networks (CNNs), leading to unnecessary computation on high-resolution features. In this paper, we propose a novel Spatially Adaptive feature Refinement (SAR) approach to reduce such superfluous computation. It...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 30(2021) vom: 09., Seite 9345-9358
|
|---|
| 1. Verfasser: |
Han, Yizeng
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Huang, Gao,
Song, Shiji,
Yang, Le,
Zhang, Yitian,
Jiang, Haojun |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2021
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
|---|
| Schlagworte: | Journal Article |
|---|