This paper is concerned with the matching stability problem across different decoder layers in DEtection TRansformers (DETR). We point out that the unstable matching in DETR is caused by a multi-optimization path problem, which is highlighted by the one-to-one matching design in DETR. To address this problem, we show that the most important design is to use and only use positional metrics (like IOU) to supervise classification scores of positive examples. Under the principle, we propose two simple yet effective modifications by integrating positional metrics to DETR's classification loss and matching cost, named position-supervised loss and position-modulated cost. We verify our methods on several DETR variants. Our methods show consistent improvements over baselines. By integrating our methods with DINO, we achieve 50.4 and 51.5 AP on the COCO detection benchmark using ResNet-50 backbones under 12 epochs and 24 epochs training settings, achieving a new record under the same setting. We achieve 63.8 AP on COCO detection test-dev with a Swin-Large backbone. Our code will be made available at https://github.com/IDEA-Research/Stable-DINO.

翻译：本文关注检测Transformer（DETR）中不同解码器层之间的匹配稳定性问题。我们指出，DETR中的不稳定性匹配是由多优化路径问题导致的，而DETR的一对一匹配设计加剧了该问题。为解决这一问题，我们证明最重要的设计原则是仅且必须使用位置度量（如IOU）来监督正样本的分类得分。基于该原则，我们提出两种简单而有效的改进方法：将位置度量分别集成到DETR的分类损失和匹配代价中，即位置监督损失和位置调制代价。我们在多种DETR变体上验证了所提方法，结果表明这些方法相较于基线模型均具有一致性提升。将我们的方法与DINO结合后，在COCO检测基准上使用ResNet-50骨干网络，在12轮和24轮训练设置下分别达到50.4和51.5 AP，创下相同设置下的新纪录。使用Swin-Large骨干网络时，在COCO检测测试集上达到63.8 AP。我们的代码将开源至https://github.com/IDEA-Research/Stable-DINO。