mIoU: 53.6
Papers with Code · CC BY-SA 4.0
Source-Free Domain Adaptation
Source-Free Domain Adaptation (SFDA) is a domain adaptation method in machine learning and computer vision where the goal is to adapt a pre-trained model to a new, target domain without access to the source domain data. This approach is advantageous in scenarios where sharing the source data is impractical due to privacy concerns, data size, or proprietary restrictions
논문
Accuracy: 89.6
Average Accuracy: 86.7
mIoU: 51.8
AP50: 35.4
Accuracy: 87.8
Average Accuracy: 72.4
AP50: 50.8
Accuracy: 87.3
Accuracy: 82.9
Average Accuracy: 84.0
Accuracy: 93.2
Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation
AP50: 40.9
AP50: 38.8
Accuracy: 85.9
Accuracy: 85.4
mIoU: 73.3
AP50: 37.1
mIoU: 60.1
AP50: 34.3
AP50: 39.7
AP50: 39.9
AP50: 40.3
AP50: 45.0
Accuracy: 87.3
AP50: 35.8