An Empirical Study on Multi-domain Robust Semantic Segmentation

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 comprehensive analysis to assess the impact of various training schemes and model selection on multi-domain learning with extensive experiments. Based on the analysis, we propose a robust solution that consistently enhances the model performance across different domains. Our solution ranks 2nd on RVC 2022 semantic segmentation task, with a dataset only 1/3 size of the 1st model used.