Plug-and-Play, Dense-Label-Free Extraction of Open-Vocabulary Semantic Segmentation from Vision-Language Models.
Jiayun LuoSiddhesh KhandelwalLeonid SigalBoyang LiPublished in: CoRR (2023)
Keyphrases
- language model
- semantic segmentation
- language modeling
- spoken term detection
- conditional random fields
- probabilistic model
- superpixels
- n gram
- weakly supervised
- information retrieval
- computer vision
- object categories
- scene classification
- information extraction
- multi label
- object class
- object segmentation
- automatic extraction
- machine learning
- multiscale
- training data
- natural language processing
- input image
- relevance model
- active learning