论文标题
矩阵：一个新的比例和纵横比意识到对象检测的体系结构
MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection
论文作者
论文摘要
我们提出矩阵（XNET），这是一种用于对象检测的新的深层体系结构。 XNET映射具有相似尺寸和宽高比的对象分为许多专业层，从而允许XNET提供比例和长宽比意识到的体系结构。我们利用XNET来增强单阶段对象检测框架。首先，我们将XNET应用于基于锚的对象检测上，为此，我们预测对象中心并回归左上角和右下角。其次，我们通过预测左上角和右下角的角来使用矩阵来进行基于角的对象检测。每个角落都预测对象的中心位置。我们还通过用中心回归替换嵌入层来增强基于角的检测。我们的最终体系结构在MS Coco上实现了47.8的地图，该地图高于其Cornernet的+5.6地图，同时也缩小了单阶段和两个阶段探测器之间的差距。该代码可在https://github.com/arashwan/matrixnet上找到。
We present MatrixNets (xNets), a new deep architecture for object detection. xNets map objects with similar sizes and aspect ratios into many specialized layers, allowing xNets to provide a scale and aspect ratio aware architecture. We leverage xNets to enhance single-stage object detection frameworks. First, we apply xNets on anchor-based object detection, for which we predict object centers and regress the top-left and bottom-right corners. Second, we use MatrixNets for corner-based object detection by predicting top-left and bottom-right corners. Each corner predicts the center location of the object. We also enhance corner-based detection by replacing the embedding layer with center regression. Our final architecture achieves mAP of 47.8 on MS COCO, which is higher than its CornerNet counterpart by +5.6 mAP while also closing the gap between single-stage and two-stage detectors. The code is available at https://github.com/arashwan/matrixnet.
