PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kang, Zhengjian, Zhuang, Jun, Mo, Kangtong, Chen, Qi, Liu, Rui, Zhang, Ye
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912977179901952
author Kang, Zhengjian
Zhuang, Jun
Mo, Kangtong
Chen, Qi
Liu, Rui
Zhang, Ye
author_facet Kang, Zhengjian
Zhuang, Jun
Mo, Kangtong
Chen, Qi
Liu, Rui
Zhang, Ye
contents Detection Transformer (DETR) has redefined object detection by casting it as a set prediction task within an end-to-end framework. Despite its elegance, DETR and its variants still rely on fixed learnable queries and suffer from severe query utilization imbalance, which limits adaptability and leaves the model capacity underused. We propose PaQ-DETR (Pattern and Quality-Aware DETR), a unified framework that enhances both query adaptivity and supervision balance. It learns a compact set of shared latent patterns capturing global semantics and dynamically generates image-specific queries through content-conditioned weighting. In parallel, a quality-aware one-to-many assignment strategy adaptively selects positive samples based on localizatio-classification consistency, enriching supervision and promoting balanced query optimization. Experiments on COCO, CityScapes, and other benchmarks show consistent gains of 1.5%-4.2% mAP across DETR backbones, including ResNet and Swin-Transformer. Beyond accuracy improvement, our method provides interpretable insights into how dynamic patterns cluster semantically across object categories.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06917
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection
Kang, Zhengjian
Zhuang, Jun
Mo, Kangtong
Chen, Qi
Liu, Rui
Zhang, Ye
Computer Vision and Pattern Recognition
Detection Transformer (DETR) has redefined object detection by casting it as a set prediction task within an end-to-end framework. Despite its elegance, DETR and its variants still rely on fixed learnable queries and suffer from severe query utilization imbalance, which limits adaptability and leaves the model capacity underused. We propose PaQ-DETR (Pattern and Quality-Aware DETR), a unified framework that enhances both query adaptivity and supervision balance. It learns a compact set of shared latent patterns capturing global semantics and dynamically generates image-specific queries through content-conditioned weighting. In parallel, a quality-aware one-to-many assignment strategy adaptively selects positive samples based on localizatio-classification consistency, enriching supervision and promoting balanced query optimization. Experiments on COCO, CityScapes, and other benchmarks show consistent gains of 1.5%-4.2% mAP across DETR backbones, including ResNet and Swin-Transformer. Beyond accuracy improvement, our method provides interpretable insights into how dynamic patterns cluster semantically across object categories.
title PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.06917