Research map / Detection and segmentation / CNN features
Cascade R-CNN: High Quality Object Detection and Instance Segmentation
Zhaowei Cai, Nuno M. Vasconcelos
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 cascade of detectors with increasing IoU thresholds (Cascade R-CNN) | FPN+ ResNet-50 · COCO val AP90 | AP90: 7.1 -> 15.8 | Improved |
| add iterative BBox regression at inference | FPN+ baseline · COCO val | AP: 34.9 -> 35.4 | No clear effect |
| add integral loss with three classifiers | FPN+ baseline · COCO val | AP90: 7.1 -> 6.9 | No clear effect |
| increase IoU threshold across stages (ablation) | Cascade R-CNN · COCO val | AP: 36.8 -> 38.5 | Improved |
| update regression statistics per stage (ablation) | Cascade R-CNN · COCO val | AP: 38.5 -> 38.9 | Improved |
| use avg stage loss weighting instead of decay (ablation) | Cascade R-CNN · COCO val | AP90: 15.8 -> 16.2 | Mixed |
| add a second stage (ablation) | FPN+ baseline · COCO val | AP: 34.9 -> 38.2 | Improved |
| add a third stage (ablation) | 2-stage Cascade R-CNN · COCO val | AP: 38.2 -> 38.9 | Improved |
| add a 4th stage (u=0.75) (ablation) | 3-stage Cascade R-CNN · COCO val | AP: 38.9 -> 38.6 | No clear effect |
| add cascade to detectors across architectures | Faster R-CNN, R-FCN, FPN+ · COCO test-dev | AP: 38.8 -> 42.8 | Improved |
| add mask head to the last stage rather than the first (ablation) | Cascade Mask R-CNN · COCO val instance segmentation | mask AP: 35.0 -> 35.4 | Improved |
| add a mask branch to every stage (ablation) | Cascade Mask R-CNN · COCO val instance segmentation | mask AP: 35.4 -> 35.5 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 2 of 2 shared results
- CornerNet — CornerNet: Detecting Objects as Paired Keypoints (ECCV 2018) · better on 1 of 1 shared result
- 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
- Cascade R-CNN: Delving Into High Quality Object Detection (CVPR 2018 · similarity 0.97)
- Hybrid Task Cascade for Instance Segmentation (CVPR 2019 · similarity 0.90)
- R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016 · similarity 0.88)
- R-FCN++: Towards Accurate Region-Based Fully Convolutional Networks for Object Detection (AAAI 2018 · similarity 0.87)
- Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning (ICCV 2019 · similarity 0.87)
- Region-Based Convolutional Networks for Accurate Object Detection and Segmentation (TPAMI 2016 · 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.
