Kernel Self-Attention for Weakly-supervised Image Classification using Deep Multiple Instance Learning.
Dawid RymarczykAdriana BorowaJacek TaborBartosz ZielinskiPublished in: WACV (2021)
Keyphrases
- weakly supervised learning
- multiple instance learning
- weakly supervised
- image classification
- semi supervised
- multi class
- supervised learning
- topic models
- object class
- semi supervised learning
- bag of words
- superpixels
- image representation
- relation extraction
- data sets
- image features
- feature extraction
- image annotation
- named entities
- visual features
- unsupervised learning
- feature space
- object detection
- small number
- support vector
- face recognition
- feature selection