Research map / Detection and segmentation / Weakly supervised detection and segmentation
Active Teacher for Semi-Supervised Object Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 iterative active sampling to initialize and augment the labeled set | Active-Teacher · MS-COCO val2017, 1% labeled | mAP (50:95): 20.75 -> 22.20 | Helped |
| Use iterative active sampling to initialize and augment the labeled set | Active-Teacher · MS-COCO val2017, 2% labeled | mAP (50:95): 24.30 -> 24.99 | Helped |
| Use iterative active sampling to initialize and augment the labeled set | Active-Teacher · MS-COCO val2017, 5% labeled | mAP (50:95): 28.27 -> 30.07 | Helped |
| Use iterative active sampling to initialize and augment the labeled set | Active-Teacher · MS-COCO val2017, 10% labeled | mAP (50:95): 31.50 -> 32.58 | Helped |
| Use iterative active sampling to initialize and augment the labeled set | Active-Teacher · MS-COCO val2017, 20% labeled | mAP (50:95): 34.88* -> 35.49 | Helped |
| Use iterative active sampling to initialize and augment the labeled set | Active-Teacher · MS-COCO val2017, 40% labeled | mAP (50:95): 37.29 -> 37.92 | Helped |
| Replace STAC's initial labeled data with Active-Teacher-selected data | STAC · MS-COCO val2017, 1% labeled | mAP (50:95): 13.97 -> 14.79 | Helped |
| Replace STAC's initial labeled data with Active-Teacher-selected data | STAC · MS-COCO val2017, 5% labeled | mAP (50:95): 24.38 -> 26.19 | Helped |
| Replace STAC's initial labeled data with Active-Teacher-selected data | STAC · MS-COCO val2017, 10% labeled | mAP (50:95): 28.64 -> 29.77 | Helped |
| Add active sampling instead of using the no-active-sampling baseline (ablation) | Active-Teacher · COCO-Standard, 5% labeled | mAP (50:95): 27.84 -> 29.48 | Helped |
| Add active sampling instead of using the no-active-sampling baseline (ablation) | Active-Teacher · COCO-Standard, 10% labeled | mAP (50:95): 31.39 -> 32.08 | Helped |
| Add active sampling instead of using the no-active-sampling baseline (ablation) | Active-Teacher · COCO-Standard, 20% labeled | mAP (50:95): 34.26* -> 35.13 | Helped |
Closest papers by meaning
- Humble Teachers Teach Better Students for Semi-Supervised Object Detection (CVPR 2021 · similarity 0.93)
- Unbiased Teacher for Semi-Supervised Object Detection (ICLR 2021 · similarity 0.92)
- Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework (CVPR 2021 · similarity 0.92)
- DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection (NeurIPS 2022 · similarity 0.91)
- A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection (CVPR 2024 · similarity 0.88)
- Stable Mean Teacher for Semi-supervised Video Action 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.