Weakly Supervised Object Localization (WSOL) is a technique for obtaining the object location from attention maps of the classification network, without using bounding box annotations. Existing WSOL approaches lack the modeling of the correlations between different regions of the target object. Hence they can only locate some discriminative attentions, which are small and sparse. Besides, they introduce too many background attentions when mining more object parts. In this paper, we propose a novel Adaptive Attention Augmentor (A³) to adaptively augment the target object attentions on class attention maps. It can supplement object attentions by discovering the semantic correspondence between different regions and dynamically suppress background attentions through the proposed Focal Dice loss. Extensive experiments demonstrate the effectiveness of our approach. On the ILSVRC dataset, A³ achieves a new state-of-the-art localization performance. On the fine-grained datasets including CUB-200-2011 and Cars-196, it also achieves very competitive results.

弱监督对象定位（WSOL）是一种用于从分类网络的关注地图中获取对象位置的技术，而无需使用边界框注释。现有的WSOL方法缺乏目标对象不同区域之间相关性的建模。因此，他们只能找到一些小而稀疏的歧视性注意力。此外，在挖掘更多对象零件时，它们会引起过多的背景注意。在本文中，我们提出了一种新颖的自适应注意力增强器（A ³），以在类注意地图上自适应地增加目标对象的注意。它可以通过发现不同区域之间的语义对应关系来补充对象的注意，并通过提出的Focal Dice损失来动态地抑制背景注意。大量的实验证明了我们方法的有效性。在ILSVRC数据集上，A ³获得了最新的本地化性能。在包括CUB-200-2011和Cars-196的细粒度数据集上，它也获得了非常有竞争力的结果。