Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training models on multiple existing domains is desired to increase the output label-space. Current research shows that there is potential to improve accuracy across datasets by using multi-domain training, but this has not yet been successfully extended to datasets of three different non-overlapping domains without manual labelling. In this paper a method for this is proposed for the datasets Cityscapes, SUIM and SUN RGB-D, by creating a label-space that spans all classes of the datasets. Duplicate classes are merged and discrepant granularity is solved by keeping classes separate. Results show that accuracy of the multi-domain model has higher accuracy than all baseline models together, if hardware performance is equalized, as resources are not limitless, showing that models benefit from additional data even from domains that have nothing in common.
翻译:语义分解模型只在其培训的领域表现良好,培训的数据集很少,而且往往有很小的标签空间,因为所需的像素级注释非常昂贵。因此,关于多个现有域的培训模型希望增加输出标签空间。当前研究表明,通过使用多域培训,有可能提高数据集的准确性。但是,这还没有成功地推广到三个不同非重叠域的数据集,而没有手工标签。在本文中,为数据集、SUIM和SUN RGB-D提议了一种方法,通过创建一个覆盖数据集所有类别的标签空间。重复类是合并的,不同的颗粒通过保持分类解决。结果显示,如果硬件性能相等,因为资源不是无限的,多域模型的准确性比所有基线模型加在一起还要高,因为硬件性能并不无限,表明即使没有共同的域也能从更多的数据中受益。