论文标题
基于排名的平衡损耗函数,将对象检测中的分类和本地化统一
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection
论文作者
论文摘要
我们建议对对象检测中的分类和本地化任务均基于统一,有限,平衡和排名的损失函数,这是一个平均局部化核心验证(ALRP)。 ALRP扩展了位置重新计算(LRP)性能度量标准(Oksuz等,2018),灵感来自平均精度(AP)损失如何将精度扩展到分类的基于排名的损失函数(Chen等,2020)。 ALRP具有以下不同的优势:(i)ALRP是分类和本地化任务的第一个基于排名的损失函数。 (ii)由于对这两个任务都使用排名,ALRP自然会实施高质量分类的高质量本地化。 (iii)ALRP在积极因素和负面之间提供了可证明的平衡。 (iv)与最先进的探测器的损失功能中的平均$ \ sim $ 6超级参数相比,ALRP损失只有一个超参数,我们在实践中没有调整。在可可数据集中,ALRP损失改善了基于排名的前身AP损失,高达$ 5 $ AP点,无需测试时间增加即可达到$ 48.9 $ AP,并且表现优于所有单级探测器。代码可在以下网址提供:https://github.com/kemaloksuz/alrploss。
We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection. aLRP extends the Localisation-Recall-Precision (LRP) performance metric (Oksuz et al., 2018) inspired from how Average Precision (AP) Loss extends precision to a ranking-based loss function for classification (Chen et al., 2020). aLRP has the following distinct advantages: (i) aLRP is the first ranking-based loss function for both classification and localisation tasks. (ii) Thanks to using ranking for both tasks, aLRP naturally enforces high-quality localisation for high-precision classification. (iii) aLRP provides provable balance between positives and negatives. (iv) Compared to on average $\sim$6 hyperparameters in the loss functions of state-of-the-art detectors, aLRP Loss has only one hyperparameter, which we did not tune in practice. On the COCO dataset, aLRP Loss improves its ranking-based predecessor, AP Loss, up to around $5$ AP points, achieves $48.9$ AP without test time augmentation and outperforms all one-stage detectors. Code available at: https://github.com/kemaloksuz/aLRPLoss .