Token Pooling in Vision Transformers for Image Classification.
Dmitrii MarinJen-Hao Rick ChangAnurag RanjanAnish PrabhuMohammad RastegariOncel TuzelPublished in: WACV (2023)
Keyphrases
- image classification
- spatial pooling
- spatial pyramid matching
- bag of words
- vision system
- computer vision
- feature extraction
- image features
- visual features
- image representation
- soft assignment
- visual words
- scene classification
- class specific
- image processing
- bag of features
- real time
- multi label
- active vision
- artificial intelligence
- databases
- visual categorization