Command Palette
Search for a command to run...
MSeg 多域语义分割复合数据集

MSeg 是一个多域语义分割复合数据集。该数据集统一了来自不同领域的语义分割数据集:COCO 、 ADE20K 、 Mapillary 、 IDD 、 BDD 、 Cityscapes 和 SUN RGB-D 。通过协调分类、合并和拆分类,得到了一个包含 194 个类别的统一分类。 为了使像素级的标注符合统一的分类法,作者通过 Mechanical Turk 平台进行了大规模的标注工作,并通过重新标记对象掩码在数据集中生成兼容的标注。
Citation
@InProceedings{MSeg_2020_CVPR, author = {Lambert, John and Liu, Zhuang and Sener, Ozan and Hays, James and Koltun, Vladlen}, title = {{MSeg}: A Composite Dataset for Multi-domain Semantic Segmentation}, booktitle = {Computer Vision and Pattern Recognition (CVPR)}, year = {2020} } @article{Lambert23tpami_MSeg, author={Lambert, John and Liu, Zhuang and Sener, Ozan and Hays, James and Koltun, Vladlen}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, title={MSeg: A Composite Dataset for Multi-Domain Semantic Segmentation}, year={2023}, volume={45}, number={1}, pages={796-810}, doi={10.1109/TPAMI.2022.3151200} }