Weakly supervised object localization (WSOL) aims to localize objects with only image-level labels. Previous methods often try to utilize feature maps and classification weights to localize objects using image level annotations indirectly. In this paper, we demonstrate that weakly supervised object localization should be divided into two parts: class-agnostic object localization and object classification. For class-agnostic object localization, we should use class-agnostic methods to generate noisy pseudo annotations and then perform bounding box regression on them without class labels. We propose the pseudo supervised object localization (PSOL) method as a new way to solve WSOL. Our PSOL models have good transferability across different datasets without fine-tuning. With generated pseudo bounding boxes, we achieve 58.00% localization accuracy on ImageNet and 74.74% localization accuracy on CUB-200, which have a large edge over previous models.

本文提出了一种新的弱监督目标定位方法，称为伪监督目标定位（PSOL）方法，将弱监督目标定位分为类不可知对象定位和对象分类两个部分，并使用PSOL方法生成噪声伪标注来进行类不可知对象定位，并在此基础上进行边界框回归，通过此方法生成的伪边界框，在未进行精调的情况下，在ImageNet数据集上实现了58.00%的定位精度和CUB-200数据集上的74.97%的定位精度，具有很好的可迁移性。

重新思考弱监督目标定位的路线