Open-vocabulary segmentation is bottlenecked by CLIP's weak region-level classification, mask proposer quality, the no-object mask filter, and COCO-ADE20K annotation conflicts, each quantified with oracle experiments.
Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolu- tion, and fully connected crfs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
What Holds Back Open-Vocabulary Segmentation?
Open-vocabulary segmentation is bottlenecked by CLIP's weak region-level classification, mask proposer quality, the no-object mask filter, and COCO-ADE20K annotation conflicts, each quantified with oracle experiments.