Title
GLiT: Neural Architecture Search for Global and Local Image Transformer
Abstract
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones are found to achieve impressive performance for image recognition. However, the transformer is designed for NLP tasks and thus could be sub-optimal when directly used for image recognition. In order to improve the visual ...
Year
DOI
Venue
2021
10.1109/ICCV48922.2021.00008
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Keywords
DocType
ISBN
Computer vision,Visualization,Image recognition,Correlation,Computer architecture,Evolutionary computation,Transformers
Conference
978-1-6654-2812-5
Citations 
PageRank 
References 
0
0.34
0
Authors
9
Name
Order
Citations
PageRank
Boyu Chen175.16
Peixia Li242.09
Chuming Li322.07
Baopu Li453.79
Lei Bai5216.90
LIN, CHEN623.40
Ming Sun79116.25
Junjie Yan8128858.19
Wanli Ouyang964.18