iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection
AAAI, pp. 13122-13129, 2020.
Training an object detector on a data-rich domain and applying it to a data-poor one with limited performance drop is highly attractive in industry, because it saves huge annotation cost. Recent research on unsupervised domain adaptive object detection has verified that aligning data distributions between source and target images throug...More
PPT (Upload PPT)