Recent proposed DETR variants have made tremendous progress in various scenarios due to their streamlined processes and remarkable performance. However, the learned queries usually explore the global context to generate the final set prediction, resulting in redundant burdens and unfaithful results. More specifically, a query is commonly responsible for objects of different scales and positions, which is a challenge for the query itself, and will cause spatial resource competition among queries. To alleviate this issue, we propose Team DETR, which leverages query collaboration and position constraints to embrace objects of interest more precisely. We also dynamically cater to each query member's prediction preference, offering the query better scale and spatial priors. In addition, the proposed Team DETR is flexible enough to be adapted to other existing DETR variants without increasing parameters and calculations. Extensive experiments on the COCO dataset show that Team DETR achieves remarkable gains, especially for small and large objects. Code is available at \url{https://github.com/horrible-dong/TeamDETR}.

翻译：[translated abstract in Chinese] 近期提出的DETR变体因其简化的流程和卓越的性能在各种场景中取得了巨大进展。然而，学习得到的查询通常通过探索全局上下文来生成最终的集合预测，这导致了冗余的负担和不可靠的结果。具体而言，一个查询通常需要处理不同尺度和位置的物体，这对查询本身构成了挑战，并将引发查询间的空间资源竞争。为缓解该问题，我们提出了Team DETR，通过利用查询协作与位置约束来更精确地捕捉目标物体。我们还动态适应每个查询成员的预测偏好，为查询提供更好的尺度和空间先验信息。此外，所提出的Team DETR具有足够的灵活性，可适配至其他现有DETR变体，且无需增加参数和计算量。在COCO数据集上的大量实验表明，Team DETR取得了显著性能提升，尤其针对小物体和大物体。代码发布于\url{https://github.com/horrible-dong/TeamDETR}。