mAP: 40.2R-1: 76.6R-5: 90.2R-10: 92.1
Papers with Code · CC BY-SA 4.0
Unsupervised Domain Adaptation
Unsupervised Domain Adaptation is a learning framework to transfer knowledge learned from source domains with a large number of annotated training examples to target domains with unlabeled data only.
<span class="description-source">Source: Domain-Specific Batch Normalization for Unsupervised Domain Adaptation </span>
논문
mIoU: 75.2
mAP: 25.1R-1: 48.8R-5: 72.8R-10: -
Accuracy (Top-1): 85
mAP: 29.9R-1: 67.0R-5: 88.5R-10: -
mAP: 30.6rank-1: 61.4rank-5: 73.3rank-10: 78.2
mAP: 41.9rank-1: 69.5rank-5: 80.3rank-10: 84.4
mAP: 31.4R-1: 59.9R-5: 80.7R-10: -
mAP: 24.1R-1: 59.1R-5: 76.2R-10: -
mAP: 34.7R-1: 73.4R-5: 88.8R-10: -
mAP: 6.35rank-1: 20.59rank-5: 31.67rank-10: 37.04
mAP: 27.7R-1: 55.6R-5: 77.4R-10: -
Accuracy: 63.7
mAP: 1.9rank-1: 6.8
Accuracy: 52.4
mAP: 3.3rank-1: 11.8rank-5: -rank-10: 27.4
mIoU: 74.4
Accuracy: 49.8
pi/6 accuracy: 94.0
mAP: 23.2rank-1: 49.5rank-5: 62.2rank-10: 67.7
Accuracy: 53.7
mAP: 33.2rank-1: 62.3rank-5: 74.1rank-10: 78.5
mAP: 30.0R-1: 68.4R-5: 85.3R-10: -
mAP: 32.7rank-1: 62.4rank-5: 72.7rank-10: 78.4
mIoU: 73.9