The purpose of weakly supervised object localization (WSOL) is to localize an object requiring only classification labels. However, most WSOL methods tend to find a specific part of an object. Further, they introduce more complex optimization problems than the classification problem to compensate for the lack of resources such as bounding box annotation. To be more efficient WSOL, we propose a new architecture that utilizes feature pyramid network (FPN) and multi-scale information to deal with simplified optimization and to improve the localization. In our proposed model, FPN produces multi-scale and high-quality feature maps, and then these feature maps are gathered to conduct classification. Therefore, we can use high-quality and abundant information for localization, which induces several advantages. First, our proposed model improves localization. Second, we don’t have to require solving complex optimization problem. In particular, the second advantage alleviates a significant burden such as hyperparameter tuning. Also, we confirmed through experiments that our proposed method outperforms state-of-the-art methods on the CUB-200-2011 and ILSVRC datasets.

弱监督对象定位（WSOL）的目的是定位仅需要分类标签的对象。但是，大多数WSOL方法都倾向于找到对象的特定部分。此外，与分类问题相比，它们引入了更复杂的优化问题，以补偿资源不足（例如边界框注释）的问题。为了提高WSOL的​​效率，我们提出了一种新的体系结构，该体系结构使用特征金字塔网络（FPN）和多尺度信息来处理简化的优化并改善定位。在我们提出的模型中，FPN生成多尺度和高质量的特征图，然后收集这些特征图以进行分类。因此，我们可以使用高质量和丰富的信息进行本地化，从而带来许多优势。第一的，我们提出的模型改善了本地化。第二，我们不必要求解决复杂的优化问题。特别地，第二个优点减轻了诸如超参数调整之类的显着负担。此外，我们通过实验证实，我们提出的方法优于CUB-200-2011和ILSVRC数据集上的最新方法。