A training-free attention reweighting method, Reverse Contrast Attention, is claimed to improve referring object detection in 11 of 15 VLMs, but the custom FitAP metric ranks boxes by IoU with ground truth, which makes the evaluation circular.
Transformer inter- pretability beyond attention visualization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Interpretable Open-Vocabulary Referring Object Detection with Reverse Contrast Attention
A training-free attention reweighting method, Reverse Contrast Attention, is claimed to improve referring object detection in 11 of 15 VLMs, but the custom FitAP metric ranks boxes by IoU with ground truth, which makes the evaluation circular.