Research map / Detection and segmentation / 3D detection and driving
Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection
Qianjiang Hu, Daizong Liu, Wei Hu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Raise the pseudo-label confidence threshold to 0.8 (ablation) | DTS · nuScenes → KITTI | AP_3D: 67.2 -> 11.7 | Hurt |
| Use a pseudo-label confidence threshold around 0.6 (ablation) | DTS · nuScenes → KITTI | AP_3D: 67.2 | Improved |
| Remove edge weight alignment from ELC by setting gamma to 0.0 (ablation) | DTS · nuScenes → KITTI | AP_3D: 66.6 -> 64.9; drops by 2.8 | Hurt |
| Remove GLR alignment from ELC by setting gamma to 1.0 (ablation) | DTS · nuScenes → KITTI | AP_3D: 66.6 -> 62.9; drops by 4.8 | Hurt |
| Add target-domain labels (10%, 20%, or 50%) | DTS · nuScenes → KITTI | AP_3D: 66.6; 67.6; 69.5; 72.4 | Improved |
| Add SN | DTS · nuScenes → KITTI | AP_3D: 66.6 -> 67.0 | Improved |
Closest papers by meaning
- LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection (ECCV 2022 · similarity 0.91)
- Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection (CVPR 2024 · similarity 0.88)
- DiffuBox: Refining 3D Object Detection with Point Diffusion (NeurIPS 2024 · similarity 0.88)
- An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains (CVPR 2024 · similarity 0.88)
- CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection (AAAI 2024 · similarity 0.88)
- Towards Learning Group-Equivariant Features for Domain Adaptive 3D Detection (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
