Research map / Point clouds / Segmentation and detection
AGO-Net: Association-Guided 3D Point Cloud Object Detection Network
Liang Du, Xiaoqing Ye, Xiao Tan, Edward Johns, Bo Chen, Errui Ding, Xiangyang Xue, Jianfeng Feng
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 |
|---|---|---|---|
| add CFG object-wise domain adaptation (ablation) | PFE baseline · KITTI val Car 3D Moderate (R40) | AP3D: 83.03 -> 84.21 | Improved |
| add SC-reweight on top of CFG (ablation) | AGO-Net · KITTI val Car 3D Moderate (R40) | AP3D: 84.21 -> 84.84 | Improved |
| add spatial attention only in SC-reweight (ablation) | AGO-Net CFG · KITTI val Car 3D Moderate (R40) | AP3D: 84.21 -> 84.75 | Improved |
| add channel attention only in SC-reweight (ablation) | AGO-Net CFG · KITTI val Car 3D Moderate (R40) | AP3D: 84.21 -> 84.32 | Improved |
| train on real plus conceptual data without adaptation (ablation) | baseline · KITTI val Car 3D Moderate (R40) | AP3D: 83.03 -> 82.97 | No clear effect |
| train on conceptual data only, test on real (ablation) | baseline · KITTI val Car 3D Moderate (R40) | AP3D: 83.03 -> 72.55 | Hurt |
| add conceptual model onto object with close-point removal instead of replacing (ablation) | AGO-Net · KITTI val Car 3D Moderate (R40) | AP3D: 84.38 -> 84.84 | Improved |
| adapt F_box instead of F_class only (ablation) | AGO-Net CFG · KITTI val Car 3D Moderate (R40) | AP3D: 83.16 -> 84.21 | Improved |
| adapt F_box instead of F_box + F_class (ablation) | AGO-Net CFG · KITTI val Car 3D Moderate (R40) | AP3D: 84.10 -> 84.21 | No clear effect |
| add AGO to PointPillars | PointPillars · KITTI val Car 3D Moderate (R11) | AP3D: 76.44 -> 78.53 | Improved |
| add AGO to SECOND | SECOND · KITTI val Car 3D Moderate (R11) | AP3D: 77.12 -> 78.82 | Improved |
| add deformable conv layer (ablation) | AGO-Net without attention · KITTI val Car 3D Moderate (R40) | AP3D: 84.21 -> 84.39 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- 3DSSD — 3DSSD: Point-Based 3D Single Stage Object Detector (CVPR 2020) · better on 4 of 4 shared results
- PV-RCNN — PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection (CVPR 2020) · better on 2 of 4 shared results
- PointPillars — PointPillars: Fast Encoders for Object Detection From Point Clouds (CVPR 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network (TPAMI 2020 · similarity 0.92)
- Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection (CVPR 2020 · similarity 0.92)
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (CVPR 2018 · similarity 0.91)
- Not All Points Are Equal: Learning Highly Efficient Point-Based Detectors for 3D LiDAR Point Clouds (CVPR 2022 · similarity 0.91)
- Towards A Weakly Supervised Framework for 3D Point Cloud Object Detection and Annotation (TPAMI 2021 · similarity 0.91)
- Structure Aware Single-Stage 3D Object Detection From Point Cloud (CVPR 2020 · similarity 0.90)
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.
