Anchor-based detectors have been continuously developed for object detection. However, the individual anchor box makes it difficult to predict the boundary's offset accurately. Instead of taking each bounding box as a closed individual, we consider using multiple boxes together to get prediction boxes. To this end, this paper proposes the \textbf{Box Decouple-Couple(BDC) strategy} in the inference, which no longer discards the overlapping boxes, but decouples the corner points of these boxes. Then, according to each corner's score, we couple the corner points to select the most accurate corner pairs. To meet the BDC strategy, a simple but novel model is designed named the \textbf{Anchor-Intermediate Detector(AID)}, which contains two head networks, i.e., an anchor-based head and an anchor-free \textbf{Corner-aware head}. The corner-aware head is able to score the corners of each bounding box to facilitate the coupling between corner points. Extensive experiments on MS COCO show that the proposed anchor-intermediate detector respectively outperforms their baseline RetinaNet and GFL method by $\sim$2.4 and $\sim$1.2 AP on the MS COCO test-dev dataset without any bells and whistles. Code is available at: https://github.com/YilongLv/AID.

翻译：基于锚点的目标检测器持续发展，但单个锚点框难以准确预测边界偏移。不同于将每个边界框视作闭合个体，本文提出在推理过程中同时利用多个框获取预测框，具体提出**边界框解耦-耦合（Box Decouple-Couple, BDC）策略**，该策略不再丢弃重叠框，而是解耦这些框的角点，随后根据每个角点的得分耦合角点以选择最精确的角点对。为适配BDC策略，本文设计了一个简洁且新颖的模型——**锚点中间检测器（Anchor-Intermediate Detector, AID）**，该模型包含两个头部网络：基于锚点的检测头与无锚点的**角点感知头**。角点感知头可为每个边界框的角点评分，便于角点间的耦合。在MS COCO数据集上的大量实验表明，所提锚点中间检测器无需任何额外技巧，即可在MS COCO测试集上分别超越基线RetinaNet和GFL方法约2.4及1.2 AP。代码已开源：https://github.com/YilongLv/AID。