期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
卷 33, 期 1, 页码 213-227出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2021.3109084
关键词
Noisy class labels; instance segmentation; foreground-background sub-task; foreground-instance sub-task; self-supervised learning
A novel method is proposed in this paper to address the issues of annotation confusion and misleading in instance segmentation. Different loss functions are used for different sub-tasks to provide correct gradient guidance, and contrastive self-supervised loss is applied to update features. Extensive experiments demonstrate the effectiveness of this method in various noisy class label scenarios.
Deep learning methods have achieved significant progress in the presence of correctly annotated datasets in instance segmentation. However, object classes in large-scale datasets are sometimes ambiguous, which easily causes confusion. Besides, limited experience and knowledge of annotators can lead to mislabeled object semantic classes. To solve this issue, a novel method is proposed in this paper, which considers different roles of noisy class labels in different sub-tasks. Our method is based on two basic observations: firstly, the foreground-background annotation of a sample is correct even though its class label is noisy. Secondly, symmetric loss benefits the model robustness to noisy labels but harms the learning of hard samples, while cross entropy loss is the opposite. Based on the two basic observations, in the foreground-background sub-task, cross entropy loss is used to fully exploit correct gradient guidance. In the foreground-instance sub-task, symmetric loss is used to prevent incorrect gradient guidance provided by noisy class labels. Furthermore, we apply contrastive self-supervised loss to update features of all foreground, to compensate for insufficient guidance provided by partially correct labels especially in the highly noisy setting. Extensive experiments conducted with three popular datasets (i.e., Pascal VOC, Cityscapes and COCO) have demonstrated the effectiveness of our method in a wide range of noisy class label scenarios.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据