ViT-AE++: Improving Vision Transformer Autoencoder for Self-supervised Medical Image Representations.
Chinmay PrabhakarHongwei Bran LiJiancheng YangSuprosanna ShitBenedikt WiestlerBjoern H. MenzePublished in: CoRR (2023)
Keyphrases
- image representation
- image classification
- multiscale
- image content
- bag of words
- quadtree
- sparse coding
- image retrieval
- feature representations
- visual words
- image features
- object recognition
- computer vision
- vision system
- receptive fields
- fuzzy logic
- representation scheme
- sparse representation
- spatial pyramid matching
- image classification and retrieval
- image processing
- low level features
- scene classification
- learning algorithm
- visual recognition tasks
- fault diagnosis
- feature space
- active vision
- high dimensional