LarvSeg uses image classification data and a category-wise attentive classifier to extend semantic segmentation to 21,000 categories without mask labels for new categories.
IEEE transactions on pattern analysis and machine intelligence 40(4), 834–848 (2017)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LarvSeg: Exploring Image Classification Data For Large Vocabulary Semantic Segmentation via Category-wise Attentive Classifier
LarvSeg uses image classification data and a category-wise attentive classifier to extend semantic segmentation to 21,000 categories without mask labels for new categories.