Object-aware Instance Labeling for Weakly Supervised Object Detection
Object-aware Instance Labeling for Weakly Supervised Object Detection
复制标题
用于弱监督对象检测的对象感知实例标记
DOI：
10.11370/isj.59.585
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Satoshi Kosugi and Toshihiko Yamasaki
中科院分区：
文献类型：
--
作者：
小柳 陽光;鳴海 拓志;大村 廉;Satoshi Kosugi and Toshihiko Yamasaki
弱监督目标检测，即检测器只用图像级别的注释进行训练，正吸引着更多的关注。作为获得性能良好的检测器的方法，迭代地更新检测器和实例标签。在本研究中，为了更有效地迭代更新，我们重点研究了实例标注问题，即根据上次定位结果为每个区域标注哪个标注的问题，并提出了两种实例标注方法。首先，为了解决只覆盖部分对象的区域往往被标记为正的问题，我们找到了覆盖整个对象的区域，重点关注上下文分类的损失。其次，考虑到图像中的其他对象可以被标记为负对象的情况，我们对被标记为负对象的区域施加了空间限制。使用这些方法，我们在Pascal VOC 2007和2012数据集上获得了最好的结果。
Weakly supervised object detection, where a detector is trained with only image-level annotations, is attracting more attention. As a method to obtain a well-performing detector, the detector and the instance labels are updated iteratively. In this study, for more efficient iterative updating, we focus on the instance labeling problem, a problem of which label should be annotated to each region based on the last localization result, and two instance labeling methods are proposed. First, to solve the problem that regions covering only some parts of the object tend to be labeled as positive, we find regions covering the whole object focusing on the context classification loss. Second, considering the situation where the other objects in the image can be labeled as negative, we impose a spatial restriction on regions labeled as negative. Using these methods, we obtain the best results on the PASCAL VOC 2007 and 2012 datasets.