DS-Net++ : Dynamic Weight Slicing for Efficient Inference in CNNs and Vision Transformers
Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference. However, their practical runtime usually lags behind the theoretical acceleration due to inefficient sparsity. In this paper, we explor...
Ausführliche Beschreibung
Bibliographische Detailangaben
Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 4 vom: 09. Apr., Seite 4430-4446
|
1. Verfasser: |
Li, Changlin
(VerfasserIn) |
Weitere Verfasser: |
Wang, Guangrun,
Wang, Bing,
Liang, Xiaodan,
Li, Zhihui,
Chang, Xiaojun |
Format: | Online-Aufsatz
|
Sprache: | English |
Veröffentlicht: |
2023
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
Schlagworte: | Journal Article |