End-to-end object detection is rapidly progressed after the emergence of DETR. DETRs use a set of sparse queries that replace the dense candidate boxes in most traditional detectors. In comparison, the sparse queries cannot guarantee a high recall as dense priors. However, making queries dense is not trivial in current frameworks. It not only suffers from heavy computational cost but also difficult optimization. As both sparse and dense queries are imperfect, then \emph{what are expected queries in end-to-end object detection}? This paper shows that the expected queries should be Dense Distinct Queries (DDQ). Concretely, we introduce dense priors back to the framework to generate dense queries. A duplicate query removal pre-process is applied to these queries so that they are distinguishable from each other. The dense distinct queries are then iteratively processed to obtain final sparse outputs. We show that DDQ is stronger, more robust, and converges faster. It obtains 44.5 AP on the MS COCO detection dataset with only 12 epochs. DDQ is also robust as it outperforms previous methods on both object detection and instance segmentation tasks on various datasets. DDQ blends advantages from traditional dense priors and recent end-to-end detectors. We hope it can serve as a new baseline and inspires researchers to revisit the complementarity between traditional methods and end-to-end detectors. The source code is publicly available at \url{https://github.com/jshilong/DDQ}.
翻译:在 DETR 出现后, 终端到终端对象的检测会迅速进展。 DETR 使用一组稀少的查询, 以取代大多数传统探测器中密集的候选框。 相比之下, 稀少的查询无法保证高提醒的提醒密度。 然而, 在当前框架中, 使查询密度不小。 不仅具有沉重的计算成本, 而且也难以优化。 由于稀疏和密集的查询都是不完善的, 那么在端到终端对象的检测中, 就会有什么预期的查询? 本文显示, 期望的查询应该为 DDQ 。 具体地说, 我们引入密集的先前查询, 以生成密度的查询。 重复的查询前处理前程序被应用到这些查询中, 以便彼此区别。 然后, 密集的不同查询被反复处理, 以获得最后的稀疏输出。 我们显示, DDQ 是更强、 更坚固和更快的。 在 MS CO 检测数据集数据集中, 仅获得12 epoch 的 AP 。 DDQ 也非常稳健, 因为它超越了在目标检测和图像前端再分析器中,, 我们可以将利用了在最近的 Rest- Q- devisur- descregistry