LSeg achieves competitive zero-shot semantic segmentation by contrastively aligning dense pixel embeddings from a transformer with text embeddings of class labels.
Few-shot open-set recognition using meta-learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Language-driven Semantic Segmentation
LSeg achieves competitive zero-shot semantic segmentation by contrastively aligning dense pixel embeddings from a transformer with text embeddings of class labels.