arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.04221cs.CV
收藏

多领域鲁棒语义分割的实证研究

An Empirical Study on Multi-Domain Robust Semantic Segmentation

Beihang University(北京航空航天大学);Hangzhou Innovation Institute, Beihang University(北京航空航天大学杭州创新研究院)

Yajie Liu, Pu Ge, Qingjie Liu, Shichao Fan, Yunhong Wang

摘要:

如何有效地利用现有的大量数据集来训练一个鲁棒的、高性能的模型对于许多实际应用具有重要意义。然而,由于标注冲突和领域分歧,在不同数据集的朴素合并上训练的模型往往会获得较差的性能。本文尝试在多个流行度分割数据集上训练一个期望跨领域表现良好的统一模型。我们从数据增强、训练策略、和模型容量。在分析的基础上,我们提出了一个强大的解决方案,能够提高跨领域的模型泛化。我们的解决方案在RVC 2022语义分割任务中排名第二,数据集只有第一个模型的1/3大小。

英文摘要:

How to effectively leverage the plentiful existing datasets to train a robust and high-performance model is of great significance for many practical applications. However, a model trained on a naive merge of different datasets tends to obtain poor performance due to annotation conflicts and domain divergence.In this paper, we attempt to train a unified model that is expected to perform well across domains on several popularity segmentation datasets.We conduct a detailed analysis of the impact on model generalization from three aspects of data augmentation, training strategies, and model capacity.Based on the analysis, we propose a robust solution that is able to improve model generalization across domains.Our solution ranks 2nd on RVC 2022 semantic segmentation task, with a dataset only 1/3 size of the 1st model used.

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。

↑