论文标题
半锚定检测器用于一阶段对象检测
Semi-Anchored Detector for One-Stage Object Detection
论文作者
论文摘要
标准的一阶段检测器由两个任务组成：分类和回归。为特征图中的每个位置引入了不同形状的锚，以减轻多尺度对象回归的挑战。但是，由于锚点中高度的阶级失效问题，分类的性能会降低。最近，已经提出了许多无锚算法直接对位置进行分类。无锚的策略受益于分类任务，但由于缺乏先前的边界框，可以为回归任务带来SUP-optimum。在这项工作中，我们提出了一个半锚框架。具体而言，我们确定了分类中的积极位置，并将多个锚与回归中的积极位置相关联。以RESNET-101为骨干，所提出的半锚检测器在可可数据集上获得了43.6％的地图，这证明了一阶段检测器之间的最新性能。
A standard one-stage detector is comprised of two tasks: classification and regression. Anchors of different shapes are introduced for each location in the feature map to mitigate the challenge of regression for multi-scale objects. However, the performance of classification can degrade due to the highly class-imbalanced problem in anchors. Recently, many anchor-free algorithms have been proposed to classify locations directly. The anchor-free strategy benefits the classification task but can lead to sup-optimum for the regression task due to the lack of prior bounding boxes. In this work, we propose a semi-anchored framework. Concretely, we identify positive locations in classification, and associate multiple anchors to the positive locations in regression. With ResNet-101 as the backbone, the proposed semi-anchored detector achieves 43.6% mAP on COCO data set, which demonstrates the state-of-art performance among one-stage detectors.
