Research map / Label-efficient and robust learning / Knowledge distillation
Beyond the Limitation of Monocular 3D Detector via Knowledge Distillation
Yiran Yang, Dongshuo Yin, Xuee Rong, Xian Sun, Wenhui Diao, Xinming Li
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 |
|---|---|---|---|
| use L2 instead of KL divergence for classification distillation (ablation) | prediction distillation · KITTI val Car | 3D AP Mod: 11.18 -> 11.26 | No clear effect |
| add depth attention module to prediction distillation (ablation) | L2 prediction distillation · KITTI val Car | 3D AP Mod: 11.26 -> 11.80 | Improved |
| weight objects by ground-truth depth with exponential mapping instead of linear (ablation) | prediction distillation · KITTI val Car | 3D AP Mod: 11.45 -> 12.22 | Improved |
| add perspective-induced feature imitation to prediction distillation (ablation) | depth-guided prediction distillation · KITTI val Car | 3D AP Mod: 12.25 -> 13.24 | Improved |
| add depth-guided prediction distillation to feature imitation (ablation) | perspective-induced feature imitation · KITTI val Car | 3D AP Mod: 12.75 -> 13.24 | Improved |
| set perspective amplitude A=0.3 versus A=0.5 (ablation) | perspective matrix · KITTI val Car | BEV AP | Mixed |
| apply distillation to student ResNet18 | PGD ResNet18 · KITTI val Car | 3D AP Mod: 11.61 -> 14.12 | Improved |
| apply distillation to MobileNetV2 student (T:ResNet101) | PGD MobileNetV2 · KITTI val Car | 3D AP Mod: 7.09 -> 7.96 | Improved |
| apply distillation to SMOKE DLA34 student | SMOKE DLA34 · KITTI val Car | 3D AP Mod: 6.01 -> 7.79 | Improved |
| use depth-aware distillation versus FGD on nuScenes | ResNet18 student · nuScenes val | mAP: 24.9 -> 25.1 | Improved |
Closest papers by meaning
- Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection (AAAI 2023 · similarity 0.92)
- Advancing 3D Object Detection With Depth-Aware Spatial Knowledge Distillation (TPAMI 2025 · similarity 0.92)
- MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection (CVPR 2025 · similarity 0.90)
- DFD: Distilling the Feature Disparity Differently for Detectors (ICML 2024 · similarity 0.89)
- Weakly Supervised Monocular 3D Detection with a Single-View Image (CVPR 2024 · similarity 0.89)
- DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Distillation for Object Detection (AAAI 2025 · 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.
