TL;DR该论文提出了一种基于卷积神经网络和 Class Activation Mapping 等方法的、自我检查图像中信息区域、并在迭代分类中关注对分类问题有用的区域的方法,可在多个数据集上实现有竞争力的甚至最先进的结果。
Abstract
convolutional neural networks have been shown to develop internal
representations, which correspond closely to semantically meaningful objects
and parts, although trained solely on class labels. class activation mapping