PaQ-DETR：学习模式与质量感知的动态查询用于目标检测
PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection
提出基于共享潜模式动态生成图像特定查询的机制，以及基于定位-分类一致性的质量感知一对多分配策略，可直接用于改进DETR类检测器的查询设计与监督平衡。
原文依据 dynamically generates image-specific queries through content-conditioned weighting
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论检测 Transformer（DETR）通过将目标检测视为端到端框架内的集合预测任务，重新定义了目标检测。尽管其设计优雅，DETR 及其变体仍依赖固定的可学习查询，并遭受严重的查询利用不平衡问题，这限制了适应性并导致模型容量未被充分利用。我们提出 PaQ-DETR（模式与质量感知 DETR），一个统一的框架，同时增强查询自适应性和监督平衡性。它学习一组紧凑的共享潜模式以捕获全局语义，并通过内容条件加权动态生成图像特定的查询。同时，一种质量感知的一对多分配策略基于定位-分类一致性自适应地选择正样本，丰富监督并促进平衡的查询优化。在 COCO、CityScapes 及其他基准上的实验表明，在包括 ResNet 和 Swin-Transformer 在内的 DETR 骨干网络上，平均精度均值（mAP）一致提升 1.5%-4.2%。除精度提升外，我们的方法还提供了关于动态模式如何跨目标类别进行语义聚类的可解释性见解。
英文原文摘要 1143 字符
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 localization-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.