TeD-Loc improves weakly supervised object localization by distilling CLIP text embeddings to patch embeddings through contrastive alignment plus a localization-guided classifier and QR orthogonalization of text embeddings.
Pay attention to your neighbours: Training-free open-vocabulary se- mantic segmentation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TeD-Loc: Text Distillation for Weakly Supervised Object Localization
TeD-Loc improves weakly supervised object localization by distilling CLIP text embeddings to patch embeddings through contrastive alignment plus a localization-guided classifier and QR orthogonalization of text embeddings.