Reproduce “From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Shuangzhi Li, Junlong Shen, Lei Ma, Xingyu Li
The method adapts LiDAR detectors to new domains and categories using few labeled target examples. It fuses camera-derived semantic cues with 3D features, constrains box search with LiDAR geometry, and refines proposals using learnable class prototypes. On five-shot NuScenes-to-KITTI, VoxelRCNN achieves 11.72% novel-class mAP, versus 1.18% for GFS-Det; this is benchmark evidence and remains below full-target supervision.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.