Pith. sign in

=#๐‘ค!#"$ #โ‹…&๐‘Š%โ‹…๐‘ž#( (1) The relation weight ๐‘ค'-* captures both geometric and attention-based relationships be-tween queries, which is computed as: ๐‘ค!#

Our proposed progressive relation-aware attention is applied into the self-attention in the decoder component · 2017

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

LP-DETR: Layer-wise Progressive Relations for Object Detection

cs.CV ยท 2025-02-07 ยท conditional ยท novelty 4.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • LP-DETR: Layer-wise Progressive Relations for Object Detection cs.CV ยท 2025-02-07 ยท conditional ยท none ยท ref 3

    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.