mIoU: 67
Papers with Code · CC BY-SA 4.0
Domain Adaptation
Domain Adaptation is the task of adapting models across domains. This is motivated by the challenge where the test and training datasets fall from different data distributions due to some factor. Domain adaptation aims to build machine learning models that can be generalized into a target domain and dealing with the discrepancy across domain distributions.
Further readings:
<span style="color:grey; opacity: 0.6">( Image credit: Unsupervised Image-to-Image Translation Networks )</span>
논문
mIoU: 52.6
mIoU: 64.3
mIoU: 46.2
mIoU: 49.1
mIoU: 60.9
mIoU: 46.7
mIoU: 56.9
mIoU: 46.8
mIoU: 60.9
mIoU: 55.0
mIoU: 48.4
mIoU: 50.6
mIoU: 60.1
mIoU: 65.8
mIoU: 78.1Extra Manual Annotation: Yes
mIoU: 63.8
mIoU: 49.8
mIoU: 76.6Extra Manual Annotation: Yes
mIoU: 51.3
Average Accuracy: 42%
mIoU: 67.3
mIoU: 68.2
mIoU: 61.6
mIoU: 51.8
mIoU: 51.2
mIoU: 69.3