论文标题
一阶段检测器中的分类改进
Improvement of Classification in One-Stage Detector
论文作者
论文摘要
视网膜提出了分类任务的焦点损失，并大大改善了一阶段探测器。但是，它与两个阶段探测器之间仍然存在差距。我们分析了视网膜的预测，并发现分类和定位的未对准是主要因素。大多数预测的框，其带有地面框的IOU大于0.5，而它们的分类分数低于0.5，这表明仍需要优化分类任务。在本文中，我们为此问题提出了一个对象置信任务，并与分类任务共享功能。该任务在样品和基础框之间使用ious作为目标，并且仅在训练中使用阳性样本的损失，这可以增加分类任务培训中阳性样本的减肥。同样，分类分数和对象置信度的联合将用于指导NMS。我们的方法不仅可以改善分类任务，而且可以减轻分类和本地化的未对准。为了评估该方法的有效性，我们在Coco 2017数据集上展示了我们的实验。如果没有哨声和铃铛，我们的方法可以在相同的培训配置下分别使用RESNET50和RESNET101的可可验证数据集提高AP的0.7％和1.0％，并且可以在两次训练时间内实现38.4％的AP。代码为：http：//github.com/chenzuge1/retinanet-conf.git。
RetinaNet proposed Focal Loss for classification task and improved one-stage detectors greatly. However, there is still a gap between it and two-stage detectors. We analyze the prediction of RetinaNet and find that the misalignment of classification and localization is the main factor. Most of predicted boxes, whose IoU with ground-truth boxes are greater than 0.5, while their classification scores are lower than 0.5, which shows that the classification task still needs to be optimized. In this paper we proposed an object confidence task for this problem, and it shares features with classification task. This task uses IoUs between samples and ground-truth boxes as targets, and it only uses losses of positive samples in training, which can increase loss weight of positive samples in classification task training. Also the joint of classification score and object confidence will be used to guide NMS. Our method can not only improve classification task, but also ease misalignment of classification and localization. To evaluate the effectiveness of this method, we show our experiments on MS COCO 2017 dataset. Without whistles and bells, our method can improve AP by 0.7% and 1.0% on COCO validation dataset with ResNet50 and ResNet101 respectively at same training configs, and it can achieve 38.4% AP with two times training time. Code is at: http://github.com/chenzuge1/RetinaNet-Conf.git.
