Research map / Detection and segmentation / CNN features
Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization
Xue Yang, Gefan Zhang, Xiaojiang Yang, Yue Zhou, Wentao Wang, Jin Tang, Tao He, Junchi Yan
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 |
|---|---|---|---|
| replace Smooth L1 with GWD loss (D_oc) | RetinaNet · DOTA-v1.0 | mAP50: 65.73 -> 68.93 | Improved |
| replace Smooth L1 with KLD loss (D_oc) | RetinaNet · DOTA-v1.0 | mAP50: 65.73 -> 71.28 | Improved |
| replace Smooth L1 with BCD loss (D_oc) | RetinaNet · DOTA-v1.0 | mAP50: 65.73 -> 71.23 | Improved |
| replace Smooth L1 with KLD loss (D_le) | RetinaNet · DOTA-v1.0 | mAP50: 64.17 -> 68.88 | Improved |
| replace Smooth L1 with KLD loss | RetinaNet · HRSC2016 | AP50:95: 47.76 -> 57.80 | Improved |
| replace Smooth L1 with KLD loss | R3Det · HRSC2016 | AP75: 43.42 -> 77.38 | Improved |
| replace Smooth L1 with KLD loss | RetinaNet · FDDB | AP85: 12.67 -> 42.20 | Improved |
| replace Smooth L1 with GWD loss | RetinaNet · MSRA-TD500 | Hmean50: 70.98 -> 76.76 | Improved |
| replace Smooth L1 with BCD loss | RetinaNet · ICDAR2015 (R+F) | Hmean85: 11.59 -> 10.53 | Hurt |
| replace Smooth L1 with KLD loss | PointPillars · KITTI val | mAP moderate: 64.28 -> 66.19 | Improved |
| replace Smooth L1 with GWD loss | PointPillars · KITTI val car 3-D | Easy AP: 88.26 -> 87.38 | Hurt |
| add normalization by Eq. to Smooth L1 (ablation) | RetinaNet · HRSC2016 | Hmean50:95: 47.76 -> 43.47 | Hurt |
Closest papers by meaning
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence (NeurIPS 2021 · similarity 0.93)
- ReDiffDet: Rotation-equivariant Diffusion Model for Oriented Object Detection (CVPR 2025 · similarity 0.86)
- GauCho: Gaussian Distributions with Cholesky Decomposition for Oriented Object Detection (CVPR 2025 · similarity 0.86)
- FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection (AAAI 2024 · similarity 0.86)
- Rethinking Boundary Discontinuity Problem for Oriented Object Detection (CVPR 2024 · similarity 0.86)
- R2Det: Exploring Relaxed Rotation Equivariance in 2D Object Detection (ICLR 2025 · similarity 0.85)
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.
