Research map / Detection and segmentation / 3D detection and driving
Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU Supervision
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| replace RDIoU with GCIoU | CT-Stack · KITTI val, Car (IoU=0.7) | moderate AP: 79.61 -> 80.03 | Helped |
| add gradient correction for angle regression (ablation) | CT-Stack with -ln(IoU) · KITTI val, Car (IoU=0.7) | moderate AP: 78.12 -> 78.81 | Helped |
| add gradient rescaling for shape regression (ablation) | CT-Stack with -ln(IoU) · KITTI val, Car (IoU=0.7) | moderate AP: 78.12 -> 78.54 | Helped |
| combine gradient correction and gradient rescaling (ablation) | CT-Stack with -ln(IoU) · KITTI val, Car (IoU=0.7) | moderate AP: 78.12 -> 80.03 | Helped |
| use P(θ)=θα with α=5 (ablation) | GCIoU angular correction · KITTI val, Car (IoU=0.7) | moderate AP: 78.81 -> 77.35 | Hurt |
| use g(θ)=θ instead of the selected correction (ablation) | GCIoU angular correction · KITTI val, Car (IoU=0.7) | moderate AP: 78.53 -> 78.23 | Hurt |
| use g(θ)=tan θ instead of the selected correction (ablation) | GCIoU angular correction · KITTI val, Car (IoU=0.7) | moderate AP: 78.53 -> 78.36 | No clear effect |
Closest papers by meaning
- Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression (CVPR 2019 · similarity 0.93)
- Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression (AAAI 2020 · similarity 0.92)
- $\alpha$-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression (NeurIPS 2021 · similarity 0.90)
- Rethinking Boundary Discontinuity Problem for Oriented Object Detection (CVPR 2024 · similarity 0.87)
- SCALoss: Side and Corner Aligned Loss for Bounding Box Regression (AAAI 2022 · similarity 0.87)
- 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection (CVPR 2021 · similarity 0.87)
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.