An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.
Alexey DosovitskiyLucas BeyerAlexander KolesnikovDirk WeissenbornXiaohua ZhaiThomas UnterthinerMostafa DehghaniMatthias MindererGeorg HeigoldSylvain GellyJakob UszkoreitNeil HoulsbyPublished in: CoRR (2020)
Keyphrases
- image recognition
- image classification
- pavement distress
- image data
- wavelet packet decomposition
- image retrieval
- image features
- input image
- multiscale
- image content
- image representation
- single image
- image structure
- image analysis
- edge detection
- image segmentation
- scale space
- image collections
- pattern recognition
- multi label
- visual features
- test images
- face recognition
- n gram
- image regions
- image annotation
- neural network
- color images
- image processing