Research map / Detection and segmentation / Weakly supervised detection and segmentation
RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels
Chengzhou Li, Ping Guo, Guanchen Meng, Qi Jia, Jinyuan Liu, Zhu Liu, Xiaokang Liu, Yu Liu, Zhongxuan Luo, Xin Fan
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 EMA teacher-student framework with pseudo-labels (ablation) | Faster R-CNN supervised baseline · FSOD 5% labeled | mAP: 44.9 -> 64.3 | Improved |
| add pseudo-label reliability weighting (PLRW) (ablation) | RSOD teacher-student · FSOD 5% labeled | mAP: 64.3 -> 65.2 | Improved |
| add corner point regression loss (CPRL) (ablation) | RSOD with PLRW · FSOD 5% labeled | mAP: 65.2 -> 66.3 | Improved |
| add object mixed pseudo-labels (OMPL) (ablation) | RSOD with PLRW and CPRL · FSOD 5% labeled | mAP: 66.3 -> 67.4 | Improved |
| use RSOD instead of supervised Faster R-CNN with 5% labels | Faster R-CNN · UATD 5% labeled | mAP: 22.9 -> 34.7 | Improved |
| use RSOD instead of Pseco | semi-supervised detector · UATD 5% labeled | mAP: 32.7 -> 34.7 | Improved |
| use RSOD instead of Soft Teacher on small objects | semi-supervised detector · UATD 5% labeled | mAP (small): 11.2 -> 12.6 | Improved |
| use RSOD instead of Soft Teacher at 1% labels | semi-supervised detector · UATD 1% labeled | mAP: 23.0 -> 23.2 | No clear effect |
| set reliability scaling factor H=0.6, threshold 0.5, IoU threshold delta=0.2 (ablation) | RSOD · FSOD 5% labeled | mAP: best 67.4 | Improved |
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.
- Pseco — PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection (ECCV 2022) · better on 4 of 4 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
- S²Teacher: Step-by-step Teacher for Sparsely Annotated Oriented Object Detection (AAAI 2026 · similarity 0.86)
- Diverse Learner: Exploring Diverse Supervision for Semi-Supervised Object Detection (ECCV 2022 · similarity 0.85)
- Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection (CVPR 2025 · similarity 0.85)
- Semi-supervised Open-World Object Detection (AAAI 2024 · similarity 0.84)
- YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection (CVPR 2024 · similarity 0.84)
- A Noisy Elephant in the Room: Is Your Out-of-Distribution Detector Robust to Label Noise? (CVPR 2024 · similarity 0.83)
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.
