Research map / Detection and segmentation / Weakly supervised detection and segmentation
Semi-Supervised and Long-Tailed Object Detection with CascadeMatch
Yuhang Zang, Kaiyang Zhou, Chen Huang, Chen Change Loy
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 pseudo-labeling (CPL) (ablation) | Supervised Cascade R-CNN · LVIS v1.0 val | AP Fix: 26.3 -> 30.1 | Improved |
| Add adaptive pseudo-label mining (APM) alone (ablation) | Supervised Cascade R-CNN · LVIS v1.0 val | AP Fix rare: 19.7 -> 22.5 | Improved |
| Add APM on top of CPL (ablation) | CascadeMatch w/ CPL · LVIS v1.0 val | AP Fix: 30.1 -> 30.5 | Improved |
| Add CPL on top of APM (ablation) | CascadeMatch w/ APM · LVIS v1.0 val | AP Fix: 28.9 -> 30.5 | Improved |
| Use progressive epsilon 1.0/1.5/2.0 instead of all 0.0 (ablation) | CascadeMatch · LVIS v1.0 val | AP Fix: 29.8 -> 30.5 | Improved |
| Increase number of heads K from 1 to 3 (ablation) | CascadeMatch · LVIS v1.0 val | AP Fix: 26.4 -> 30.5 | Improved |
| Increase number of heads K from 3 to 5 (ablation) | CascadeMatch · LVIS v1.0 val | AP Fix rare: 23.1 -> 21.2 | Hurt |
| Increase unsupervised loss weight from 1.0 to 2.0 (ablation) | CascadeMatch · LVIS v1.0 val | AP Fix: 30.5 -> 29.4 | Hurt |
| Add CascadeMatch to Cascade R-CNN R-50 vs supervised baseline | Supervised Cascade R-CNN · LVIS v1.0 val | AP Fix: 26.3 -> 30.5 | Improved |
| Replace Unbiased Teacher with CascadeMatch (Sparse R-CNN PVT) | Unbiased Teacher · LVIS v1.0 val | AP Fix: 33.5 -> 35.2 | Improved |
| Add CascadeMatch to COCO-LT training | Supervised Cascade R-CNN · COCO-LT val | AP: 25.4 -> 27.8 | Improved |
| Add CascadeMatch under 40% missing labels | Cascade R-CNN + Federated Loss · LVIS 40% annotations erased | AP: 22.5 -> 24.2 | Improved |
Closest papers by meaning
- SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection (CVPR 2025 · similarity 0.89)
- Label Matching Semi-Supervised Object Detection (CVPR 2022 · similarity 0.89)
- Diverse Learner: Exploring Diverse Supervision for Semi-Supervised Object Detection (ECCV 2022 · similarity 0.88)
- Adapting Object Size Variance and Class Imbalance for Semi-supervised Object Detection (AAAI 2023 · similarity 0.88)
- Learning from Noisy Data for Semi-Supervised 3D Object Detection (ICCV 2023 · similarity 0.88)
- Semi-DETR: Semi-Supervised Object Detection With Detection Transformers (CVPR 2023 · similarity 0.88)
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.
