论文标题
3SD：没有标签的自我监管的显着性检测
3SD: Self-Supervised Saliency Detection With No Labels
论文作者
论文摘要
我们提出了一种概念上简单的自我监督方法，用于显着检测。我们的方法生成并使用伪地真相标签进行培训。生成的伪GT标签不需要任何类型的人类注释（例如，像素标签或诸如涂鸦之类的弱标签）。最近的作品表明，从分类任务中提取的功能提供了重要的显着性提示，例如图像中显着对象的结构和语义信息。我们的方法称为3SD，通过与显着对象检测并行添加一个自我监督分类任务的分支来利用这一想法，以获取类激活图（CAM MAPS）。这些CAM地图以及输入图像的边缘用于生成伪GT显着图来训练我们的3SD网络。具体来说，我们建议对分类任务的多个图像补丁进行基于对比的学习培训。与整个图像上的天真分类相比，我们显示了具有对比性损失的多斑分类和对比损失的质量。六个基准数据集的实验表明，如果没有任何标签，我们的3SD方法的表现都优于所有现有的弱监督和无监督的方法，并且其性能与完全监督的方法相当。代码可在以下网址找到：https：//github.com/rajeevyasarla/3sd
We present a conceptually simple self-supervised method for saliency detection. Our method generates and uses pseudo-ground truth labels for training. The generated pseudo-GT labels don't require any kind of human annotations (e.g., pixel-wise labels or weak labels like scribbles). Recent works show that features extracted from classification tasks provide important saliency cues like structure and semantic information of salient objects in the image. Our method, called 3SD, exploits this idea by adding a branch for a self-supervised classification task in parallel with salient object detection, to obtain class activation maps (CAM maps). These CAM maps along with the edges of the input image are used to generate the pseudo-GT saliency maps to train our 3SD network. Specifically, we propose a contrastive learning-based training on multiple image patches for the classification task. We show the multi-patch classification with contrastive loss improves the quality of the CAM maps compared to naive classification on the entire image. Experiments on six benchmark datasets demonstrate that without any labels, our 3SD method outperforms all existing weakly supervised and unsupervised methods, and its performance is on par with the fully-supervised methods. Code is available at :https://github.com/rajeevyasarla/3SD
