论文标题
通过点击监督学习对象刻度以进行对象检测
Learning Object Scale With Click Supervision for Object Detection
论文作者
论文摘要
弱监督的对象检测最近引起了人们越来越多的关注，因为它仅需要图像关注。但是，与完全监督对象检测方法相比，现有方法获得的性能仍然远非令人满意。为了在注释成本和对象检测性能之间实现良好的权衡，我们提出了一种简单而有效的方法，该方法将可视化的可视化与点击监督结合起来，以生成伪造真实性（即界框）。这些伪基真实扫描可用于训练完全监督的检测器。为了估计对象量表，我们首先采用建议选择算法来保留高质量的建议，然后通过称为“空间注意卡”的Propated CNN可视化算法为这些保留的建议生成分类图（CAM）。最后，我们将这些凸轮融合在一起，以生成伪造真相，并将完全监督的对象探测器与这些基础真相一起训练。 PASCAL VOC2007和VOC 2012数据集的实验结果表明，与最新的基于图像级的方法和基于中心点击的方法相比
Weakly-supervised object detection has recently attracted increasing attention since it only requires image-levelannotations. However, the performance obtained by existingmethods is still far from being satisfactory compared with fully-supervised object detection methods. To achieve a good trade-off between annotation cost and object detection performance,we propose a simple yet effective method which incorporatesCNN visualization with click supervision to generate the pseudoground-truths (i.e., bounding boxes). These pseudo ground-truthscan be used to train a fully-supervised detector. To estimatethe object scale, we firstly adopt a proposal selection algorithmto preserve high-quality proposals, and then generate ClassActivation Maps (CAMs) for these preserved proposals by theproposed CNN visualization algorithm called Spatial AttentionCAM. Finally, we fuse these CAMs together to generate pseudoground-truths and train a fully-supervised object detector withthese ground-truths. Experimental results on the PASCAL VOC2007 and VOC 2012 datasets show that the proposed methodcan obtain much higher accuracy for estimating the object scale,compared with the state-of-the-art image-level based methodsand the center-click based method
