Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification.
Bo ZhangJiakang YuanBaopu LiTao ChenJiayuan FanBotian ShiPublished in: CoRR (2022)
Keyphrases
- fine grained
- image classification
- image features
- coarse grained
- image representation
- image retrieval
- image content
- image regions
- access control
- semantic relations
- bag of words
- visual features
- low level
- knowledge acquisition
- natural language processing
- image collections
- video sequences
- general purpose
- keywords
- object recognition
- information extraction
- probabilistic model
- machine learning