Research map / Label-efficient and robust learning / Semi-supervised learning
Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction With Extremely Limited Labels
Changrui Chen, Jungong Han, Kurt Debattista
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 VC learning to teacher-student baseline | teacher-student baseline · Pascal VOC 1/128 (mean of 3 folds) | mIoU: 50.77 -> 53.00 | Improved |
| add VC learning (ResNet101 backbone) | teacher-student baseline · Pascal VOC 1/128, fold 2 | mIoU: 50.79 -> 55.23 | Improved |
| add VC learning | teacher-student baseline · Cityscapes 1/72 (mean) | mIoU: 51.18 -> 53.02 | Improved |
| use CE instead of MSE loss in VC (ablation) | VC learning · Pascal VOC 1/64 (mean) | mIoU: 62.20 -> 62.78 | Improved |
| add virtual category to MSE loss (vs NEG only) (ablation) | VC learning · Pascal VOC 1/64 (mean) | mIoU: 61.71 -> 62.20 | Improved |
| use virtual weight with magnitude (VC) instead of cosine similarity (ablation) | VC learning · Pascal VOC 1/128 fold 1 | mIoU: 47.76 -> 48.62 | Improved |
| replace discarding confusing samples with VC (ablation) | VC learning · MS COCO 1% | mAP: 19.37 -> 20.81 | Improved |
| replace omit-and-detach with VC (ablation) | VC learning · MS COCO 1% | mAP: 19.70 -> 20.81 | Improved |
| keep all potential labels for confusing samples (ablation) | pseudo-labelling baseline · MS COCO 1% | mAP: 20.00 -> 19.36 | Hurt |
| add Reg* localisation loss on top of VC (ablation) | VC learning · MS COCO 1% | mAP: 20.81 -> 20.94 | Improved |
| use cross-model verification instead of temporal stability (ablation) | VC learning · MS COCO 1% | mAP: 20.81 -> 20.96 | Improved |
| use strong augmentation for virtual weight generation (ablation) | VC learning · MS COCO 1% | mAP: 20.81 -> 20.70 | Hurt |
Closest papers by meaning
- Semi-Supervised Object Detection via Virtual Category Learning (ECCV 2022 · similarity 0.93)
- Density-Aware Graph for Deep Semi-Supervised Visual Recognition (CVPR 2020 · similarity 0.86)
- Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency (TPAMI 2019 · similarity 0.86)
- All Labels Are Not Created Equal: Enhancing Semi-Supervision via Label Grouping and Co-Training (CVPR 2021 · similarity 0.86)
- Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching (ICLR 2023 · similarity 0.86)
- Dense Teacher: Dense Pseudo-Labels for Semi-Supervised Object Detection (ECCV 2022 · 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.
