PAT clusters multi-resolution VLM features into semantic codebook tokens and jointly trains reconstruction and segmentation, improving open-vocabulary segmentation over the SAN baseline.
Scaling open- vocabulary image segmentation with image-level labels,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Incorporating Feature Pyramid Tokenization and Open Vocabulary Semantic Segmentation
PAT clusters multi-resolution VLM features into semantic codebook tokens and jointly trains reconstruction and segmentation, improving open-vocabulary segmentation over the SAN baseline.