LP-DETR proposes a progressive relation-aware self-attention module that models local, medium, and global spatial relations between DETR queries, reaching 52.3 AP with ResNet-50 after 12 epochs on COCO, a small gain over Relation-DETR.
This paper presents LP-DETR (Layer-wise Progressive Relation DETR), a novel approach that enhances DETR-based object detection through multi-scale relation modeling
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
LP-DETR: Layer-wise Progressive Relations for Object Detection
LP-DETR proposes a progressive relation-aware self-attention module that models local, medium, and global spatial relations between DETR queries, reaching 52.3 AP with ResNet-50 after 12 epochs on COCO, a small gain over Relation-DETR.