论文标题
深入研究两个阶段对象检测中积极建议的不平衡
Delving into the Imbalance of Positive Proposals in Two-stage Object Detection
论文作者
论文摘要
对于当前对象检测模型，不平衡问题是主要但未解决的瓶颈。在这项工作中，我们观察到两个关键但从未讨论过不平衡问题。第一个不平衡在于大量低质量的RPN建议，这使得R-CNN模块（即分类后层）在早期训练阶段对负面建议高度偏见。第二个不平衡源于不同测试图像中不平衡的基地数字，导致测试阶段潜在现有的阳性建议数量的不平衡。为了解决这两个不平衡问题，我们将两项创新纳入了更快的R-CNN：1）R-CNN梯度退火（RGA）策略，以增强在早期培训阶段的积极建议的影响。 2）一组平行的R-CNN模块（PRM）在一个相同的骨架上训练期间具有不同的正/负采样比。我们的RGA和PRM在可可大师的AP上完全可以提高2.0％。关于人类的实验进一步验证了我们在各种对象检测任务中创新的有效性。
Imbalance issue is a major yet unsolved bottleneck for the current object detection models. In this work, we observe two crucial yet never discussed imbalance issues. The first imbalance lies in the large number of low-quality RPN proposals, which makes the R-CNN module (i.e., post-classification layers) become highly biased towards the negative proposals in the early training stage. The second imbalance stems from the unbalanced ground-truth numbers across different testing images, resulting in the imbalance of the number of potentially existing positive proposals in testing phase. To tackle these two imbalance issues, we incorporates two innovations into Faster R-CNN: 1) an R-CNN Gradient Annealing (RGA) strategy to enhance the impact of positive proposals in the early training stage. 2) a set of Parallel R-CNN Modules (PRM) with different positive/negative sampling ratios during training on one same backbone. Our RGA and PRM can totally bring 2.0% improvements on AP on COCO minival. Experiments on CrowdHuman further validates the effectiveness of our innovations across various kinds of object detection tasks.
