论文标题
SWA对象检测
SWA Object Detection
论文作者
论文摘要
您是否想为对象检测器改进1.0 AP，而无需任何推理成本和检测器的任何更改？让我们告诉你这样的食谱。这很简单：使用周期性学习率训练探测器为额外的12个时代训练，然后平均这12个检查点作为您的最终检测模型}。这种有效的配方灵感来自随机权重平均（SWA），该配方是在Arxiv中提出的：1803.05407，用于改善深层神经网络中的概括。我们发现它在对象检测中也非常有效。在此技术报告中，我们系统地研究将SWA应用于对象检测以及实例分割的影响。通过广泛的实验，我们发现了对物体检测执行SWA的上述可行政策，并且我们始终如一地实现$ \ sim $ 1.0 AP的改善，比在具有挑战性的可可基准上改善了各种流行探测器，包括Mask RCNN，更快的RCNN，RCNN，Retinanet，FCOS，FCOS，YOLOV3，YOLOV3和VFNET。我们希望这项工作能使更多的对象检测研究人员了解这一技术，并帮助他们训练更好的对象探测器。代码可在以下网址提供：https：//github.com/hyz-xmaster/swa_object_detection。
Do you want to improve 1.0 AP for your object detector without any inference cost and any change to your detector? Let us tell you such a recipe. It is surprisingly simple: train your detector for an extra 12 epochs using cyclical learning rates and then average these 12 checkpoints as your final detection model}. This potent recipe is inspired by Stochastic Weights Averaging (SWA), which is proposed in arXiv:1803.05407 for improving generalization in deep neural networks. We found it also very effective in object detection. In this technique report, we systematically investigate the effects of applying SWA to object detection as well as instance segmentation. Through extensive experiments, we discover the aforementioned workable policy of performing SWA in object detection, and we consistently achieve $\sim$1.0 AP improvement over various popular detectors on the challenging COCO benchmark, including Mask RCNN, Faster RCNN, RetinaNet, FCOS, YOLOv3 and VFNet. We hope this work will make more researchers in object detection know this technique and help them train better object detectors. Code is available at: https://github.com/hyz-xmaster/swa_object_detection .
