发表机构
East China Normal University; FinVolution Group（华东师范大学; 信也科技集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对DETR检测器中查询冗余导致训练不稳和预测不果断的问题，提出DETRNN模块，将无序查询转化为基于置信度和相似度的竞争序列，用RNN循环细化，减少冗余并提升精度。
AI 中文摘要
DETR风格的检测器在训练期间使用一对一的双边匹配将对象查询分配给真实目标，从而实现无需非极大值抑制（NMS）的端到端集合预测。然而，在没有显式去重过程的情况下，多个查询仍可能对同一对象产生高度相似的假设，导致训练不稳定且预测不够果断。受NMS顺序排序的启发，我们提出了DETRNN，一个即插即用模块，将无序的对象查询转化为具有竞争意识的序列，用于循环细化。DETRNN根据先前的预测构建显式的基于置信度和相似度的顺序，然后沿此顺序使用RNN细化查询，以建模解码器内部的竞争。这种有序的循环细化减少了冗余预测，稳定了优化，并提高了最终检测精度。在多个DETR风格检测器上的实验显示，在相当效率下获得了一致的性能提升。
英文摘要
DETR-style detectors use one-to-one bipartite matching during training to assign object queries to ground-truth objects, enabling end-to-end set prediction without non-maximum suppression (NMS). However, without an explicit de-duplication procedure, multiple queries can still produce highly similar hypotheses for the same object, making training unstable and predictions less decisive. Inspired by the sequential ordering of NMS, we propose DETRNN, a plug-and-play module that turns unordered object queries into a competition-aware sequence for recurrent refinement. DETRNN builds an explicit confidence-and-similarity based order from prior predictions, then refines queries with an RNN along this order to model competition inside the decoder. This ordered recurrent refinement reduces redundant predictions, stabilizes optimization, and improves final detection accuracy. Experiments on multiple DETR-style detectors show consistent gains with comparable efficiency.
CommentsAccepted at NeurIPS 2026
