论文标题
NMS罢工
NMS Strikes Back
论文作者
论文摘要
检测变压器（DETR）直接通过在训练过程中使用一对一的两分匹配并启用端到端对象检测，将查询直接转换为唯一对象。最近，这些模型已经超过了可可的传统探测器，并具有不可否认的优雅性。但是，它们与多种设计中的传统探测器有所不同，包括模型架构和培训时间表，因此尚不完全了解一对一匹配的有效性。在这项工作中，我们在Detrs中的一对一匈牙利匹配与具有非最大最大监督（NMS）的传统探测器中的一对多标签分配之间进行了严格的比较。令人惊讶的是，我们观察到具有NMS的一对多作业在同一设置下始终超过标准的一对一匹配，最大增益高达2.5 map。我们使用基于IOU的标签分配训练可变形的检测器在12个时期内获得了50.2个可可地图（1倍时间表），并具有RESNET50骨架，在这种情况下优于所有现有的传统或基于变压器的检测器。在多个数据集，计划和体系结构上，我们始终显示二分匹配对于性能检测变压器不需要。此外，我们将检测变压器的成功归因于其表现力的变压器体系结构。代码可在https://github.com/jozhang97/deta上找到。
Detection Transformer (DETR) directly transforms queries to unique objects by using one-to-one bipartite matching during training and enables end-to-end object detection. Recently, these models have surpassed traditional detectors on COCO with undeniable elegance. However, they differ from traditional detectors in multiple designs, including model architecture and training schedules, and thus the effectiveness of one-to-one matching is not fully understood. In this work, we conduct a strict comparison between the one-to-one Hungarian matching in DETRs and the one-to-many label assignments in traditional detectors with non-maximum supervision (NMS). Surprisingly, we observe one-to-many assignments with NMS consistently outperform standard one-to-one matching under the same setting, with a significant gain of up to 2.5 mAP. Our detector that trains Deformable-DETR with traditional IoU-based label assignment achieved 50.2 COCO mAP within 12 epochs (1x schedule) with ResNet50 backbone, outperforming all existing traditional or transformer-based detectors in this setting. On multiple datasets, schedules, and architectures, we consistently show bipartite matching is unnecessary for performant detection transformers. Furthermore, we attribute the success of detection transformers to their expressive transformer architecture. Code is available at https://github.com/jozhang97/DETA.
