论文标题
对象检测是一个正标记的问题
Object Detection as a Positive-Unlabeled Problem
论文作者
论文摘要
与其他深度学习方法一样，标签质量对于学习现代卷积对象探测器很重要。但是，在复杂的图像场景中可以找到的对象实例的可能大量和广泛的多样性使得构成完整的注释是一项艰巨的任务。可以在各种流行对象检测数据集中观察到缺少注释的对象。这些缺失的注释可能是有问题的，因为用于训练对象检测模型的标准跨透明损失将分类视为一个正阴性（PN）问题：隐含的未标记区域被隐式地假定为背景。因此，任何缺少边界框的对象都会产生令人困惑的学习信号，我们从经验上观察到的效果。为了解决这个问题，我们建议将对象检测视为一个正标（PU）问题，该问题消除了未标记区域必须为负面的假设。我们证明，我们提出的PU分类损失优于Pascal VOC和MS Coco的标准PN损失，以及带有完整标签的视觉基因组和深层的PN损失。
As with other deep learning methods, label quality is important for learning modern convolutional object detectors. However, the potentially large number and wide diversity of object instances that can be found in complex image scenes makes constituting complete annotations a challenging task; objects missing annotations can be observed in a variety of popular object detection datasets. These missing annotations can be problematic, as the standard cross-entropy loss employed to train object detection models treats classification as a positive-negative (PN) problem: unlabeled regions are implicitly assumed to be background. As such, any object missing a bounding box results in a confusing learning signal, the effects of which we observe empirically. To remedy this, we propose treating object detection as a positive-unlabeled (PU) problem, which removes the assumption that unlabeled regions must be negative. We demonstrate that our proposed PU classification loss outperforms the standard PN loss on PASCAL VOC and MS COCO across a range of label missingness, as well as on Visual Genome and DeepLesion with full labels.
