Authors: Zhengjian Kang, Ye Zhang, Xiaoyu Deng, Xintao Li, Yongzhe Zhang
Abstract: This paper presents LP-DETR (Layer-wise Progressive DETR), a novel approach
that enhances DETR-based object detection through multi-scale relation
modeling. Our method introduces learnable spatial relationships between object
queries through a relation-aware self-attention mechanism, which adaptively
learns to balance different scales of relations (local, medium and global)
across decoder layers. This progressive design enables the model to effectively
capture evolving spatial dependencies throughout the detection pipeline.
Extensive experiments on COCO 2017 dataset demonstrate that our method improves
both convergence speed and detection accuracy compared to standard
self-attention module. The proposed method achieves competitive results,
reaching 52.3\% AP with 12 epochs and 52.5\% AP with 24 epochs using ResNet-50
backbone, and further improving to 58.0\% AP with Swin-L backbone. Furthermore,
our analysis reveals an interesting pattern: the model naturally learns to
prioritize local spatial relations in early decoder layers while gradually
shifting attention to broader contexts in deeper layers, providing valuable
insights for future research in object detection.
Source: http://arxiv.org/abs/2502.05147v1
