MiniViT: Compressing Vision Transformers with Weight Multiplexing

Vision Transformer (ViT) models have recently drawn much attention in computer vision due to their high model capability. However, ViT models suffer from huge number of parameters, restricting their applicability on devices with limited memory. To alleviate this problem, we propose MiniViT, a new co...

Celý popis

Podrobná bibliografie

Vydáno v:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 12135 - 12144
Hlavní autoři:	Zhang, Jinnian, Peng, Houwen, Wu, Kan, Liu, Mengchen, Xiao, Bin, Fu, Jianlong, Yuan, Lu
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	IEEE 01.06.2022
Témata:	Benchmark testing categorization Codes Computational modeling Computer vision Deep learning architectures and techniques; Recognition: detection Image coding Multiplexing Performance evaluation retrieval; Vision applications and systems
ISSN:	1063-6919
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!