Research map / Detection and segmentation / Weakly supervised detection and segmentation
PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection
Gang Li, Xiang Li, Yujie Wang, Yichao Wu, Ding Liang, Shanshan Zhang
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 label-level consistency via random-resize scale jitter (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 32.7 -> 33.9 | Improved |
| add feature-consistency view V2 on top of V1 (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 33.9 -> 34.9 | Improved |
| add extra downsampled view with only label consistency (vanilla multi-view) (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 33.9 vs 33.9 | No clear effect |
| add PCV regression weighting to V1 (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 33.9 -> 34.8 | Improved |
| add PLA after PCV (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 34.8 -> 35.7 | Improved |
| add PLA to V1+V2+PCV (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 36.0 -> 36.3 | Improved |
| use PCV instead of abandoning regression loss (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 33.9 -> 34.8 | Improved |
| use PCV instead of box jittering (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 34.5 -> 34.8 | Improved |
| use PCV instead of reg consistency (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 34.2 -> 34.8 | Improved |
| combine score and IoU in PLA quality (alpha 0.5 vs 0) (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 35.2 -> 35.7 | Improved |
| combine score and IoU in PLA quality (alpha 0.5 vs 1.0) (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 35.4 -> 35.7 | Improved |
| raise PLA candidate IoU threshold t from 0.4 to 0.5 (ablation) | PseCo · COCO val2017 (10% labeled, single fold) | mAP: 35.7 -> 35.5 | Hurt |
Later papers that compared with this method
9 later accepted papers report Pseco as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.
- RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels (AAAI 2026 · better on 4 of 4 shared results)
- Generalized-Scale Object Counting with Gradual Query Aggregation (AAAI 2026 · better on 1 of 1 shared result)
- Few-Shot Pattern Detection via Template Matching and Regression (ICCV 2025 · better on 2 of 2 shared results)
- A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation (NeurIPS 2024 · better on 4 of 4 shared results)
- Zero-shot Object Counting with Good Exemplars (ECCV 2024 · better on 0 of 1 shared result)
- Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection (CVPR 2023 · better on 4 of 5 shared results)
- Semi-DETR: Semi-Supervised Object Detection With Detection Transformers (CVPR 2023 · better on 3 of 3 shared results)
- Adapting Object Size Variance and Class Imbalance for Semi-supervised Object Detection (AAAI 2023 · better on 2 of 2 shared results)
1 more not listed.
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
- Adapting Object Size Variance and Class Imbalance for Semi-supervised Object Detection (AAAI 2023 · similarity 0.93)
- Rethinking Pseudo Labels for Semi-supervised Object Detection (AAAI 2022 · similarity 0.93)
- Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection (CVPR 2023 · similarity 0.92)
- Mind the Gap: Polishing Pseudo Labels for Accurate Semi-supervised Object Detection (AAAI 2023 · similarity 0.91)
- Learning from Noisy Data for Semi-Supervised 3D Object Detection (ICCV 2023 · similarity 0.91)
- Multi-clue Consistency Learning to Bridge Gaps Between General and Oriented Object in Semi-supervised Detection (AAAI 2025 · similarity 0.90)
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.
