Research map / Detection and segmentation / Weakly supervised detection and segmentation
Semi-Supervised Object Detection via Multi-Instance Alignment With Global Class Prototypes
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 |
|---|---|---|---|
| Add multi-instance alignment using global class prototypes | SoftTeacher · PASCAL VOC, VOC2007 test | mAP: 80.32 -> 81.72 | Helped |
| Add multi-instance alignment using global class prototypes | SoftTeacher · MSCOCO, 1% labeled | mAP: 20.46±0.39 -> 21.30±0.28 | Helped |
| Add multi-instance alignment using global class prototypes | SoftTeacher · MSCOCO, 5% labeled | mAP: 30.74±0.08 -> 31.67±0.16 | Helped |
| Add multi-instance alignment using global class prototypes | SoftTeacher · MSCOCO, 10% labeled | mAP: 34.04±0.14 -> 35.02±0.26 | Helped |
| Add multi-instance alignment using global class prototypes | SoftTeacher · MSCOCO, fully labeled | AP0.5:0.95: 44.50 -> 45.92 | Helped |
| Add multi-instance alignment using contrastive feature alignment instead of global class prototypes (ablation) | Baseline on PASCAL VOC · PASCAL VOC, VOC2007 test | mAP: 80.32 -> 80.53 | Helped |
| Add multi-instance alignment using Siamese feature alignment instead of global class prototypes (ablation) | Baseline on PASCAL VOC · PASCAL VOC, VOC2007 test | mAP: 80.32 -> 80.79 | Helped |
| Add multi-instance alignment with global class prototypes (ablation) | Baseline on PASCAL VOC · PASCAL VOC, VOC2007 test | mAP: 80.32 -> 81.72 | Helped |
| Replace cosine similarity with negative L2 distance (ablation) | MA-GCP on PASCAL VOC · PASCAL VOC, VOC2007 test | mAP: 81.72 -> 81.04 | Hurt |
| Set the alignment-loss weight λa to 0.8 (ablation) | MA-GCP on PASCAL VOC · PASCAL VOC | mAP | Helped |
Closest papers by meaning
- Semi-DETR: Semi-Supervised Object Detection With Detection Transformers (CVPR 2023 · similarity 0.91)
- Adapting Object Size Variance and Class Imbalance for Semi-supervised Object Detection (AAAI 2023 · similarity 0.91)
- Multi-clue Consistency Learning to Bridge Gaps Between General and Oriented Object in Semi-supervised Detection (AAAI 2025 · similarity 0.88)
- Semi-supervised Open-World Object Detection (AAAI 2024 · similarity 0.87)
- Relational Matching for Weakly Semi-Supervised Oriented Object Detection (CVPR 2024 · similarity 0.86)
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment (CVPR 2024 · similarity 0.86)
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.