Sparse Multimodal Vision Transformer for Weakly Supervised Semantic Segmentation.
Joëlle HannaMichael MommertDamian BorthPublished in: CVPR Workshops (2023)
Keyphrases
- weakly supervised
- semantic segmentation
- superpixels
- object class
- topic models
- relation extraction
- computer vision
- image processing
- sparse representation
- semi supervised
- conditional random fields
- named entities
- scene classification
- multiscale
- text mining
- segmentation method
- object segmentation
- information extraction
- active learning
- object recognition