Research map / Detection and segmentation / Weakly supervised detection and segmentation
Dense Teacher: Dense Pseudo-Labels for Semi-Supervised Object Detection
Hongyu Zhou, Zheng Ge, Songtao Liu, Weixin Mao, Zeming Li, Haiyan Yu, Jian Sun
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 |
|---|---|---|---|
| replace pseudo-boxes with dense pseudo-labels over all regions | Unbiased Teacher on FCOS · COCO-Standard 10% | AP: 31.52 -> 32.0 | Improved |
| add FRS-based region division (top k% learning region) (ablation) | Dense Teacher · COCO-Standard 10% | AP: 32.00 -> 33.34 | Improved |
| add unsupervised regression branch (ablation) | Dense Teacher · COCO-Standard 10% | AP: 33.34 -> 35.11 | Improved |
| select hard negatives instead of suppressing them (ablation) | Dense Teacher · COCO-Standard 10% | AP: 31.56 -> 33.34 | Improved |
| select hard negatives instead of ignoring them (ablation) | Dense Teacher · COCO-Standard 10% | AP: 32.64 -> 33.34 | Improved |
| learning region k=1 instead of 0.1 (ablation) | Dense Teacher · COCO-Standard 10% | AP: 25.76 -> 35.11 | Improved |
| learning region k=1 instead of 5 (ablation) | Dense Teacher · COCO-Standard 10% | AP: 33.85 -> 35.11 | Improved |
| unsupervised weight 4 instead of 8 (ablation) | Dense Teacher · COCO-Standard 10% | AP: 33.81 -> 35.11 | Improved |
| unsupervised weight 2 instead of 4 (ablation) | Dense Teacher · COCO-Full | AP: 43.04 -> 44.92 | Improved |
| replace pseudo-boxes with dense labels on anchor-based RetinaNet | Dense Teacher · COCO (RetinaNet) | AP: 28.9 -> 31.1 | Improved |
| replace pseudo-boxes with dense labels on CrowdHuman | Dense Teacher · CrowdHuman (FCOS) | mMR: 62.8 -> 60.7 | Improved |
| large scale jittering and longer schedule | Dense Teacher · COCO-Full | mAP: 43.90 -> 44.94 -> 46.12 | Improved |
Later papers that compared with this method
7 later accepted papers report Dense Teacher as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.
- LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection (ICCV 2025 · better on 4 of 4 shared results)
- Multi-clue Consistency Learning to Bridge Gaps Between General and Oriented Object in Semi-supervised Detection (AAAI 2025 · better on 1 of 1 shared result)
- Relational Matching for Weakly Semi-Supervised Oriented Object Detection (CVPR 2024 · better on 3 of 3 shared results)
- SOOD: Towards Semi-Supervised Oriented Object Detection (CVPR 2023 · better on 4 of 4 shared results)
- Semi-DETR: Semi-Supervised Object Detection With Detection Transformers (CVPR 2023 · better on 3 of 3 shared results)
- Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection (CVPR 2023 · better on 2 of 2 shared results)
- MixTeacher: Mining Promising Labels With Mixed Scale Teacher for Semi-Supervised Object Detection (CVPR 2023 · better on 1 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.
- Instant Teaching — Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework (CVPR 2021) · better on 2 of 2 shared results
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
- DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection (NeurIPS 2022 · similarity 0.92)
- Humble Teachers Teach Better Students for Semi-Supervised Object Detection (CVPR 2021 · similarity 0.92)
- End-to-End Semi-Supervised Object Detection With Soft Teacher (ICCV 2021 · similarity 0.91)
- Adapting Object Size Variance and Class Imbalance for Semi-supervised Object Detection (AAAI 2023 · similarity 0.91)
- Unbiased Teacher for Semi-Supervised Object Detection (ICLR 2021 · similarity 0.90)
- Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection (CVPR 2024 · 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.
