BriefGPT.xyz
Dec, 2020
自训练用于类增量语义分割
Self-Training for Class-Incremental Semantic Segmentation
HTML
PDF
Lu Yu, Xialei Liu, Joost van de Weijer
TL;DR
提出了一种基于自监督学习和伪标签的自训练方法，用于减轻深度神经网络在逐步学习新类任务时出现的灾难性遗忘问题，该方法不仅考虑了历史任务的知识，还利用了额外的数据提高了语义分割的性能。
Abstract
We study incremental learning for semantic segmentation where when learning new classes we have no access to the labeled data of previous tasks. When incrementally learning new classes,
deep neural networks
suffer from
→