论文标题
Dino：用改进的DeTr detr，用于端到端对象检测
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
论文作者
论文摘要
我们将Dino（\ textbf {d} etr与\ textbf {i} mpred de \ textbf {n} oinging hand \ textbf {o} r box），一种最先进的端到端对象检测器。 ％ 在本文中。 Dino通过使用一种对比度方法来降级训练，一种用于锚定初始化的混合查询选择方法以及对盒子预测的两次方案的混合查询选择方法来改善性能和效率的模型。 Dino获得$ 49.4 $ ap in $ 12 $时代和$ 51.3 $ ap in $ 24 $ in Coco的$ 24 $时代，并带有Resnet-50骨架和多尺度功能，从而显着改善了$ \ textbf {+6.0} $ \ \\ textbf {ap} $ \ textbf {ap textbf} DN-DETR，以前的最佳DITR样模型。 Dino在模型大小和数据大小上都很好地缩放。没有铃铛和哨子，在对象365数据集进行了swinl骨架的训练后，Dino在Coco \ texttt {val2017}上获得了最佳结果， （\ textbf {$ \ textbf {63.3} $ ap}）。与排行榜上的其他模型相比，Dino大大降低了其模型大小和预训练数据大小，同时实现了更好的结果。我们的代码将在\ url {https://github.com/ideacvr/dino}提供。
We present DINO (\textbf{D}ETR with \textbf{I}mproved de\textbf{N}oising anch\textbf{O}r boxes), a state-of-the-art end-to-end object detector. % in this paper. DINO improves over previous DETR-like models in performance and efficiency by using a contrastive way for denoising training, a mixed query selection method for anchor initialization, and a look forward twice scheme for box prediction. DINO achieves $49.4$AP in $12$ epochs and $51.3$AP in $24$ epochs on COCO with a ResNet-50 backbone and multi-scale features, yielding a significant improvement of $\textbf{+6.0}$\textbf{AP} and $\textbf{+2.7}$\textbf{AP}, respectively, compared to DN-DETR, the previous best DETR-like model. DINO scales well in both model size and data size. Without bells and whistles, after pre-training on the Objects365 dataset with a SwinL backbone, DINO obtains the best results on both COCO \texttt{val2017} ($\textbf{63.2}$\textbf{AP}) and \texttt{test-dev} (\textbf{$\textbf{63.3}$AP}). Compared to other models on the leaderboard, DINO significantly reduces its model size and pre-training data size while achieving better results. Our code will be available at \url{https://github.com/IDEACVR/DINO}.
