论文标题
重要性抽样凸轮对于弱监督的分割
Importance Sampling CAMs for Weakly-Supervised Segmentation
论文作者
论文摘要
分类网络可用于通过类激活图（CAM）在图像中定位和细分对象。但是，如果没有像素级注释，则已知分类网络（1）主要集中在歧视区域上，以及（2）生产散布的凸轮而没有定义明确的预测轮廓。在这项工作中，我们解决了这两个问题，并有两个贡献以改善CAM学习。首先，我们根据CAM引起的类别概率质量函数来结合重要性抽样，以产生随机图像级别的类预测。这导致凸轮在更大程度上激活对象。其次，我们制定了一个特征相似性损失项，该项旨在与图像中的边缘匹配预测轮廓。作为第三个贡献，我们对Pascal VOC 2012基准数据集进行了实验，以证明这些修饰在轮廓准确性方面显着提高了性能，同时与当前的最新方法相似。
Classification networks can be used to localize and segment objects in images by means of class activation maps (CAMs). However, without pixel-level annotations, classification networks are known to (1) mainly focus on discriminative regions, and (2) to produce diffuse CAMs without well-defined prediction contours. In this work, we approach both problems with two contributions for improving CAM learning. First, we incorporate importance sampling based on the class-wise probability mass function induced by the CAMs to produce stochastic image-level class predictions. This results in CAMs which activate over a larger extent of objects. Second, we formulate a feature similarity loss term which aims to match the prediction contours with edges in the image. As a third contribution, we conduct experiments on the PASCAL VOC 2012 benchmark dataset to demonstrate that these modifications significantly increase the performance in terms of contour accuracy, while being comparable to current state-of-the-art methods in terms of region similarity.
