论文标题
动态R-CNN：通过动态训练进行高质量的对象检测
Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training
论文作者
论文摘要
尽管近年来两阶段的对象探测器一直在不断提高最新性能，但训练过程本身远非水晶。在这项工作中，我们首先指出固定网络设置与动态培训程序之间的不一致问题，这极大地影响了性能。例如，固定的标签分配策略和回归损失函数不能符合建议的分布变化，因此对训练高质量探测器有害。因此，我们建议动态R-CNN根据训练期间的建议统计数据自动调整标签分配标准（IOU阈值）和回归损耗函数的形状（Smoothl1损失的参数）。这种动态设计可以更好地利用训练样品，并推动检测器适合更多高质量的样品。具体而言，我们的方法在MS Coco数据集上使用1.9％AP的Resnet-50-FPN基线，AP $ _ {90} $ 5.5％，没有额外的开销。代码和模型可在https://github.com/hkzhang95/dynamicrcnn上找到。
Although two-stage object detectors have continuously advanced the state-of-the-art performance in recent years, the training process itself is far from crystal. In this work, we first point out the inconsistency problem between the fixed network settings and the dynamic training procedure, which greatly affects the performance. For example, the fixed label assignment strategy and regression loss function cannot fit the distribution change of proposals and thus are harmful to training high quality detectors. Consequently, we propose Dynamic R-CNN to adjust the label assignment criteria (IoU threshold) and the shape of regression loss function (parameters of SmoothL1 Loss) automatically based on the statistics of proposals during training. This dynamic design makes better use of the training samples and pushes the detector to fit more high quality samples. Specifically, our method improves upon ResNet-50-FPN baseline with 1.9% AP and 5.5% AP$_{90}$ on the MS COCO dataset with no extra overhead. Codes and models are available at https://github.com/hkzhang95/DynamicRCNN.
