You Reap What You Sow: Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection
You Reap What You Sow: Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection
复制标题
DOI：
10.1109/cvpr.2019.00964
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Krishna Kumar Singh;Yong Jae Lee
中科院分区：
文献类型：
--
作者：
Krishna Kumar Singh;Yong Jae Lee
我们提出了一种新的方法，使用视频来获得高精度的对象建议，用于弱监督对象检测。现有的弱监督检测方法使用现成的建议方法，如边缘框或选择性搜索来获得候选框。这些方法提供了高召回率，但以数千个嘈杂的建议为代价。因此，找到少数相关对象区域的全部负担留给随后的对象挖掘步骤。为了缓解这个问题，我们专注于提高初始候选对象提案的精度。由于我们不能依赖于本地化注释，我们转向视频并利用运动线索来自动估计对象的范围，以训练弱监督区域建议网络（W-RPN）。我们使用W-RPN来生成高精度的对象建议，这些建议又用于根据它们的空间重叠来重新排列高召回率的建议，如边缘框或选择性搜索。我们的W-RPN建议导致PASCAL VOC 2007和2012上最先进的弱监督对象检测方法的性能显着提高。
We propose a novel way of using videos to obtain high precision object proposals for weakly-supervised object detection. Existing weakly-supervised detection approaches use off-the-shelf proposal methods like edge boxes or selective search to obtain candidate boxes. These methods provide high recall but at the expense of thousands of noisy proposals. Thus, the entire burden of finding the few relevant object regions is left to the ensuing object mining step. To mitigate this issue, we focus instead on improving the precision of the initial candidate object proposals. Since we cannot rely on localization annotations, we turn to video and leverage motion cues to automatically estimate the extent of objects to train a Weakly-supervised Region Proposal Network (W-RPN). We use the W-RPN to generate high precision object proposals, which are in turn used to re-rank high recall proposals like edge boxes or selective search according to their spatial overlap. Our W-RPN proposals lead to significant improvement in performance for state-of-the-art weakly-supervised object detection approaches on PASCAL VOC 2007 and 2012.