基于自监督以物体为中心的表征的无监督语义分割
Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations
AI总结：
该研究提出结合无监督显著性掩码与自监督特征聚类的无监督语义分割方法，在PASCAL VOC上远超现有前沿水平，还首次在MS COCO全81类上取得了相应结果。
摘要：
本文表明，自监督特征学习的最新进展可实现无监督物体发现与语义分割，其性能与10年前有监督语义分割的领域前沿水平相当。我们提出一种基于无监督显著性掩码与自监督特征聚类的方法，用于启动物体发现，随后在伪标签上训练语义分割网络，以在含多个物体的图像上引导系统迭代优化。我们在PASCAL VOC数据集上取得的结果远超当前前沿水平（50.0 mIoU），并首次报告了在MS COCO数据集全部81个类别上的结果：我们的方法发现了34个IoU超过20%的类别，同时全部81个类别的平均IoU为19.6。
英文摘要：
In this paper, we show that recent advances in self-supervised feature learning enable unsupervised object discovery and semantic segmentation with a performance that matches the state of the field on supervised semantic segmentation 10 years ago. We propose a methodology based on unsupervised saliency masks and self-supervised feature clustering to kickstart object discovery followed by training a semantic segmentation network on pseudo-labels to bootstrap the system on images with multiple objects. We present results on PASCAL VOC that go far beyond the current state of the art (50.0 mIoU), and we report for the first time results on MS COCO for the whole set of 81 classes: our method discovers 34 categories with more than $20\%$ IoU, while obtaining an average IoU of 19.6 for all 81 categories.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
