Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning.
Richard J. ChenChengkuan ChenYicong LiTiffany Y. ChenAndrew D. TristerRahul G. KrishnanFaisal MahmoodPublished in: CVPR (2022)
Keyphrases
- learning process
- image features
- rigid body
- learning systems
- image database
- active learning
- image data
- computer vision
- image collections
- edge detection
- input image
- image registration
- image analysis
- learning algorithm
- ground truth
- supervised learning
- image classification
- unsupervised learning
- reinforcement learning
- learning tasks
- linear predictors
- three dimensional
- image annotation
- test images
- image matching
- keypoints
- segmentation method
- feature points
- prior knowledge