论文标题
DN-DETR：通过引入查询denoising加速detr培训
DN-DETR: Accelerate DETR Training by Introducing Query DeNoising
论文作者
论文摘要
我们在本文中介绍了一种新型的DeNoisising训练方法，以加速DETR（检测变压器）训练，并深入了解类似DITR的方法的缓慢收敛问题。我们表明，较慢的收敛性是由于两分图匹配的不稳定性导致的，这在早期训练阶段导致优化目标不一致。为了解决这个问题，除了匈牙利损失外，我们的方法还将噪声带入变压器解码器，并训练模型重建原始框，从而有效地降低了匹配的两组式匹配的难度并导致更快的逆转。我们的方法是通用的，可以通过添加数十行代码来实现显着改进，可以轻松地插入任何类似DITR的方法中。结果，我们的DN-DETR在相同的设置下导致了显着的改进（$+1.9 $ ap），并在类似于DETR的方法中获得了最佳结果（AP $ 43.4 $和$ 48.6 $，分别为$ 12 $和$ 50 $的培训），带有resnet-resnet- $ 50 $ backbone。与在相同设置下的基线相比，DN-DETR以$ 50 \％$ $培训时代的表现可相当。代码可在\ url {https://github.com/fengli-ust/dn-detr}中找到。
We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results from the instability of bipartite graph matching which causes inconsistent optimization goals in early training stages. To address this issue, except for the Hungarian loss, our method additionally feeds ground-truth bounding boxes with noises into Transformer decoder and trains the model to reconstruct the original boxes, which effectively reduces the bipartite graph matching difficulty and leads to a faster convergence. Our method is universal and can be easily plugged into any DETR-like methods by adding dozens of lines of code to achieve a remarkable improvement. As a result, our DN-DETR results in a remarkable improvement ($+1.9$AP) under the same setting and achieves the best result (AP $43.4$ and $48.6$ with $12$ and $50$ epochs of training respectively) among DETR-like methods with ResNet-$50$ backbone. Compared with the baseline under the same setting, DN-DETR achieves comparable performance with $50\%$ training epochs. Code is available at \url{https://github.com/FengLi-ust/DN-DETR}.
