# LP-DETR: Layer-wise Progressive Relations for Object Detection Source: [LP-DETR: Layer-wise Progressive Relations for Object Detection]() Collection index: [llms.txt]() Data updated: 2025-10-26T04:40:15.707Z Authors: Zhengjian Kang, Ye Zhang, Xiaoyu Deng, Xintao Li, Yongzhe Zhang Published: 2025-02-07T18:25:28.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()