让检测查询动态适应图像，提升模型精度与可解释性
PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection
- 用共享语义模式生成图像特定的动态查询
- 质量感知分配策略使监督更均衡，提升1.5%-4.2% mAP
- 适合关注模型可解释性与检测精度的开发者
检测变换器（DETR）通过端到端的集合预测框架重新定义了目标检测。尽管结构优雅，现有DETR及其变体仍依赖固定可学习查询，存在严重查询利用率不平衡问题，限制了模型适应性并导致能力浪费。本文提出PaQ-DETR（Pattern and Quality-Aware DETR），一个统一框架，同时增强查询自适应性和监督平衡性。该方法学习一组紧凑的共享潜在模式以捕捉全局语义，并通过内容条件加权动态生成图像特定查询。同时，采用质量感知的一对多分配策略，根据定位与分类一致性自适应选择正样本，丰富监督信号并促进查询优化均衡。在COCO、CityScapes等基准上实验表明，对多种DETR骨干网络（包括ResNet和Swin-Transformer）均实现1.5%-4.2%的mAP提升。此外，本方法还揭示了动态模式在不同物体类别间语义聚类的可解释特性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。