Research map / Detection and segmentation / CNN features
SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
Xue Yang, Jirui Yang, Junchi Yan, Yue Zhang, Tengfei Zhang, Zhi Guo, Xian Sun, Kun Fu
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 pixel attention (ablation) | R2CNN · DOTA OBB | mAP (%): 60.67 -> 64.34 | Improved |
| add channel attention to pixel attention (MDA-Net) (ablation) | R2CNN+Pixel Attention · DOTA OBB | mAP (%): 64.34 -> 65.33 | Improved |
| add SF-Net (finer sampling and feature fusion) (ablation) | R2CNN+MDA · DOTA OBB | mAP (%): 65.33 -> 68.89 | Improved |
| add IoU-smooth L1 loss (ablation) | R2CNN+SF+MDA · DOTA OBB | mAP (%): 68.89 -> 69.83 | Improved |
| add image pyramid training and testing (ablation) | R2CNN+SF+MDA+IoU · DOTA OBB | mAP (%): 69.83 -> 72.61 | Improved |
| add supervision to the attention network (ablation) | MDA-Net · DOTA OBB | mAP (%): 61.23 -> 65.33 | Improved |
| add supervision to the attention network (ablation) | MDA-Net · VOC2007 (07+12 train) | mAP (%): 80.53 -> 82.27 | Improved |
| add shifted anchors (SA) (ablation) | R2CNN+MDA · DOTA OBB | mAP (%): 65.33 -> 62.78 | Hurt |
| add shift jittering (SJ) (ablation) | R2CNN+MDA · DOTA OBB | mAP (%): 65.33 -> 62.70 | Hurt |
| use dilated convolution to enlarge feature maps (ablation) | R2CNN+MDA · DOTA OBB | mAP (%): 65.33 -> 66.40 | Improved |
| reduce anchor stride from 16 to 6 (ablation) | SCRDet · DOTA OBB | mAP (%): 63.64 -> 67.06 | Improved |
| add MDA-Net | FPN* · COCO minival | mAP/F1: 36.1 -> 36.8 | Improved |
Later papers that compared with this method
6 later accepted papers report SCRDet as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing (TPAMI 2022 · better on 2 of 2 shared results)
- OSKDet: Orientation-Sensitive Keypoint Localization for Rotated Object Detection (CVPR 2022 · better on 1 of 1 shared result)
- Learning Modulated Loss for Rotated Object Detection (AAAI 2021 · better on 1 of 1 shared result)
- Dense Label Encoding for Boundary Discontinuity Free Rotation Detection (CVPR 2021 · better on 1 of 1 shared result)
- Oriented R-CNN for Object Detection (ICCV 2021 · better on 1 of 1 shared result)
- Dynamic Refinement Network for Oriented and Densely Packed Object Detection (CVPR 2020 · better on 0 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- R-FCN — R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016) · 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
- SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing (TPAMI 2022 · similarity 0.93)
- ReDet: A Rotation-Equivariant Detector for Aerial Object Detection (CVPR 2021 · similarity 0.86)
- SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection (AAAI 2026 · similarity 0.85)
- Adaptive Rotated Convolution for Rotated Object Detection (ICCV 2023 · similarity 0.85)
- FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection (AAAI 2024 · similarity 0.84)
- Poly Kernel Inception Network for Remote Sensing Detection (CVPR 2024 · similarity 0.83)
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.
