论文标题
SLV：空间似然投票对弱监督对象检测
SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection
论文作者
论文摘要
基于多个实例学习（MIL）的框架，巨大的作品促进了弱监督对象检测（WSOD）的进步。但是，大多数基于MIL的方法倾向于将实例定位到其判别部分而不是整个内容。在本文中，我们提出了一个空间似然投票（SLV）模块，以将提案本地化过程收敛，而无需任何有限的框注释。具体而言，给定图像中的所有区域提案都扮演选民在培训期间的每一次迭代的角色，投票支持空间维度中每个类别的可能性。在以较大的可能性值对该区域进行扩张后，投票结果被正式化为边界框，用于最终分类和本地化。根据SLV，我们进一步提出了一个多任务学习的端到端培训框架。分类和本地化任务相互促进，从而进一步提高了检测性能。 Pascal VOC 2007和2012数据集的广泛实验证明了SLV的出色性能。
Based on the framework of multiple instance learning (MIL), tremendous works have promoted the advances of weakly supervised object detection (WSOD). However, most MIL-based methods tend to localize instances to their discriminative parts instead of the whole content. In this paper, we propose a spatial likelihood voting (SLV) module to converge the proposal localizing process without any bounding box annotations. Specifically, all region proposals in a given image play the role of voters every iteration during training, voting for the likelihood of each category in spatial dimensions. After dilating alignment on the area with large likelihood values, the voting results are regularized as bounding boxes, being used for the final classification and localization. Based on SLV, we further propose an end-to-end training framework for multi-task learning. The classification and localization tasks promote each other, which further improves the detection performance. Extensive experiments on the PASCAL VOC 2007 and 2012 datasets demonstrate the superior performance of SLV.
