교환학생 (University of Mississippi)/학부연구생
[Paper Review] Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions
Difference with other methodsThis paper focuses on how to estimate 2D human poses without low-light ground truths. (only use well-lit ground-truth data)Recent studies require the use of paired well-lit and low-light images with ground truths. → Low light images have the inherent challenges associated with annotation on low-light images. Two stage1. Pre-trainingModel is trained on well-lit data w..
