REDI combines supervised TF-IDF corpus scores over DINOv3 visual words with attention maps to rank patches, reducing sequence length 46.8% while raising Top-1 accuracy from 83.514% to 84.706% on ImageNet-1K.
Understanding inverse document fre- quency: On theoretical arguments for IDF.Journal of Doc- umentation, 60(5):503–520, 2004
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
REDI: Corpus Aware Patch Ranking for DINOv3 Token Reduction
REDI combines supervised TF-IDF corpus scores over DINOv3 visual words with attention maps to rank patches, reducing sequence length 46.8% while raising Top-1 accuracy from 83.514% to 84.706% on ImageNet-1K.