The paper modifies Faster R-CNN with CLIP-based semantic alignment, feature decorrelation, and centerness-based objectness to improve open-set detection, reporting higher unknown-class precision on VOC-COCO.
Ow-detr: Open-world detection transformer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Open-Set Object Detection By Aligning Known Class Representations
The paper modifies Faster R-CNN with CLIP-based semantic alignment, feature decorrelation, and centerness-based objectness to improve open-set detection, reporting higher unknown-class precision on VOC-COCO.