We delve into pseudo-labeling for semi-supervised monocular 3D object detection (SSM3OD) and discover two primary issues: a misalignment between the prediction quality of 3D and 2D attributes and the tendency of depth supervision derived from pseudo-labels to be noisy, leading to significant optimization conflicts with other reliable forms of supervision. We introduce a novel decoupled pseudo-labeling (DPL) approach for SSM3OD. Our approach features a Decoupled Pseudo-label Generation (DPG) module, designed to efficiently generate pseudo-labels by separately processing 2D and 3D attributes. This module incorporates a unique homography-based method for identifying dependable pseudo-labels in BEV space, specifically for 3D attributes. Additionally, we present a DepthGradient Projection (DGP) module to mitigate optimization conflicts caused by noisy depth supervision of pseudo-labels, effectively decoupling the depth gradient and removing conflicting gradients. This dual decoupling strategy-at both the pseudo-label generation and gradient levels-significantly improves the utilization of pseudo-labels in SSM3OD. Our comprehensive experiments on the KITTI benchmark demonstrate the superiority of our method over existing approaches.
@article{arxiv.2403.17387,
title = {Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection},
author = {Jiacheng Zhang and Jiaming Li and Xiangru Lin and Wei Zhang and Xiao Tan and Junyu Han and Errui Ding and Jingdong Wang and Guanbin Li},
journal= {arXiv preprint arXiv:2403.17387},
year = {2024}
}