Research map / Label-efficient and robust learning / Semi-supervised learning
Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification
Zhenyu Wang, Ya-Li Li, Ye Guo, Shengjin Wang
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 |
|---|---|---|---|
| Use region uncertainty quantification to construct soft targets and train with multi-peak class probabilities | Semi-supervised Faster R-CNN · PASCAL VOC 2007 test, VOC07 labeled and VOC12 unlabeled | AP50:95: 45.2 -> 49.3 | Improved |
| Use region uncertainty quantification to construct soft targets and train with multi-peak class probabilities | Semi-supervised Faster R-CNN · COCO minival, coco-35 labeled and coco-80 unlabeled | AP50:95: 33.1 -> 35.5 | Improved |
| Add cross-category uncertainty (CCU) (ablation) | Semi-supervised detector · VOC07 test | AP50:95: 45.2 -> 46.2 | Improved |
| Add cross-category uncertainty (CCU) (ablation) | Fully supervised detector · VOC07 test | AP50:95: 43.1 -> 42.5 | Hurt |
| Add uncertainty-aware soft target (UST) (ablation) | Semi-supervised detector · VOC07 test | AP50:95: 45.2 -> 48.2 | Improved |
| Add both CCU and UST (ablation) | Semi-supervised detector · VOC07 test | AP50:95: 45.2 -> 49.3 | Improved |
| Add cross-category uncertainty (CCU) (ablation) | Semi-supervised detector · COCO minival | AP50:95: 33.1 -> 34.3 | Improved |
| Add cross-category uncertainty (CCU) (ablation) | Fully supervised detector · COCO minival | AP50:95: 31.3 -> 31.2 | No clear effect |
| Add uncertainty-aware soft target (UST) (ablation) | Semi-supervised detector · COCO minival | AP50:95: 33.1 -> 33.7 | Improved |
| Add both CCU and UST (ablation) | Semi-supervised detector · COCO minival | AP50:95: 33.1 -> 35.5 | Improved |
| Use a 3x rather than 1x training schedule | Ours on COCO minival with coco-115/coco-120 · COCO minival | AP50:95: 40.6 -> 41.7 | Improved |
| Add strong data augmentation to the 3x training schedule | Ours on COCO minival with coco-115/coco-120 · COCO minival | AP50:95: 41.7 -> 43.2 | Improved |
Closest papers by meaning
- Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection (CVPR 2021 · similarity 0.91)
- Learning from Noisy Data for Semi-Supervised 3D Object Detection (ICCV 2023 · similarity 0.90)
- Rethinking Pseudo Labels for Semi-supervised Object Detection (AAAI 2022 · similarity 0.89)
- Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection (CVPR 2023 · similarity 0.89)
- Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection (CVPR 2024 · similarity 0.87)
- Multi-clue Consistency Learning to Bridge Gaps Between General and Oriented Object in Semi-supervised Detection (AAAI 2025 · 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.
