通过优化查询质量提升小目标检测性能，解决特征噪声与匹配不准问题。
Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization
- 引入抗噪特征融合网络与相似性匹配机制，提升查询质量。
- 在多个基准上优于当前最优方法，显著改善小目标检测效果。
- 适合关注小目标检测、模型鲁棒性改进的研究者使用。
尽管基于Transformer的检测器在小目标检测（SOD）方面取得进展，但现有方法仍受特征金字塔网络（FPN）固有噪声敏感性和标签分配策略中查询质量下降的影响。本文提出一种新型抗噪查询优化（NRQO）范式，创新性地结合了抗噪特征金字塔网络（NT-FPN）和成对相似性区域提议网络（PS-RPN）。NT-FPN通过保持空间与语义信息完整性，在特征融合阶段有效缓解噪声。不同于传统标签分配策略，PS-RPN通过位置与形状相似性增强候选框与真实框的匹配，生成足够数量的高质量正样本查询，无需额外超参数。在多个基准上的大量实验一致表明，NRQO优于当前最先进方法。
原文摘要 · Abstract (English)
Despite advancements in Transformer-based detectors for small object detection (SOD), recent studies show that these detectors still face challenges due to inherent noise sensitivity in feature pyramid networks (FPN) and diminished query quality in existing label assignment strategies. In this paper, we propose a novel Noise-Resilient Query Optimization (NRQO) paradigm, which innovatively incorporates the Noise-Tolerance Feature Pyramid Network (NT-FPN) and the Pairwise-Similarity Region Proposal Network (PS-RPN). Specifically, NT-FPN mitigates noise during feature fusion in FPN by preserving spatial and semantic information integrity. Unlike existing label assignment strategies, PS-RPN generates a sufficient number of high-quality positive queries by enhancing anchor-ground truth matching through position and shape similarities, without the need for additional hyperparameters. Extensive experiments on multiple benchmarks consistently demonstrate the superiority of NRQO over state-of-the-art baselines.
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。