From Captions to Pixels: Open-Set Semantic Segmentation without Masks.
Paulis F. BarzdinsIngus Janis PretkalninsGuntis BarzdinsPublished in: Balt. J. Mod. Comput. (2024)
Keyphrases
- semantic segmentation
- street scenes
- superpixels
- label transfer
- conditional random fields
- weakly supervised
- input image
- scene classification
- object categories
- pascal voc
- bounding box
- image set
- object class
- visual features
- image understanding
- object recognition
- object classes
- higher order
- multiscale
- pixel level
- natural scenes
- bag of words
- co occurrence
- object detection