Deep supervised models possess significant capability to assimilate extensive training data, thereby presenting an opportunity to enhance model performance through training on multiple datasets. However, conflicts arising from different label spaces among datasets may adversely affect model performance. In this paper, we propose a novel approach to automatically construct a unified label space across multiple datasets using graph neural networks. This enables semantic segmentation models to be trained simultaneously on multiple datasets, resulting in performance improvements. Unlike existing methods, our approach facilitates seamless training without the need for additional manual reannotation or taxonomy reconciliation. This significantly enhances the efficiency and effectiveness of multi-dataset segmentation model training. The results demonstrate that our method significantly outperforms other multi-dataset training methods when trained on seven datasets simultaneously, and achieves state-of-the-art performance on the WildDash 2 benchmark.

翻译：深度监督模型具备吸收大量训练数据的强大能力，这为通过多数据集训练提升模型性能提供了可能。然而，不同数据集间标签空间的冲突可能对模型性能产生不利影响。本文提出一种基于图神经网络的新方法，用于自动构建跨多数据集的统一标签空间。该方法使得语义分割模型能够在多个数据集上同时进行训练，从而获得性能提升。与现有方法不同，我们的方法无需额外的人工重新标注或分类体系协调即可实现无缝训练，显著提高了多数据集分割模型训练的效率和效果。实验结果表明，在同时使用七个数据集进行训练时，我们的方法显著优于其他多数据集训练方法，并在WildDash 2基准测试中取得了最先进的性能。