One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection
This work addresses the problem of domain interference in 3D object detection for computer vision researchers, offering a novel method to unify multiple datasets, though it is incremental in improving multi-domain training.
The paper tackled the challenge of multi-domain joint training for point cloud-based 3D object detection by proposing OneDet3D, a universal model that addresses detection across diverse indoor and outdoor scenes with one set of parameters, achieving strong universal ability in experiments.
The current trend in computer vision is to utilize one universal model to address all various tasks. Achieving such a universal model inevitably requires incorporating multi-domain data for joint training to learn across multiple problem scenarios. In point cloud based 3D object detection, however, such multi-domain joint training is highly challenging, because large domain gaps among point clouds from different datasets lead to the severe domain-interference problem. In this paper, we propose \textbf{OneDet3D}, a universal one-for-all model that addresses 3D detection across different domains, including diverse indoor and outdoor scenes, within the \emph{same} framework and only \emph{one} set of parameters. We propose the domain-aware partitioning in scatter and context, guided by a routing mechanism, to address the data interference issue, and further incorporate the text modality for a language-guided classification to unify the multi-dataset label spaces and mitigate the category interference issue. The fully sparse structure and anchor-free head further accommodate point clouds with significant scale disparities. Extensive experiments demonstrate the strong universal ability of OneDet3D to utilize only one trained model for addressing almost all 3D object detection tasks.