Semi-supervised 3D detection

Current detection models in autonomous driving greatly rely on labeled data, which is expensive for the autonomous driving company. To this end, unlabeled large-scale collected data is considered to be exploited in self- or semi-supervised training. In this project, I adopt SESS, Mean Teacher, Pseudo-Label and 3DIoUMatch to my detection model. The pictures below are used to visualize pseudo-label and consistency regularization, respectively.