Inference-time α-entmax sparsification of CLIP’s final self-attention denoises diffuse mass and lifts dense open-vocabulary segmentation and region retrieval in proportion to baseline off-class spread.
International Journal of Computer Vision111(1), 98–136 (Jan 2015)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sparse Attention for Dense Open-Vocabulary Prediction in CLIP
Inference-time α-entmax sparsification of CLIP’s final self-attention denoises diffuse mass and lifts dense open-vocabulary segmentation and region retrieval in proportion to baseline off-class spread.