Research map / Video / Video segmentation and tracking
Semi-Supervised Video Semantic Segmentation With Inter-Frame Feature Reconstruction
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 inter-frame feature reconstruction (IFR) | Accel · Cityscapes val, 1/30 labeled data | mIoU: 45.73 -> 52.86 | Helped |
| Add inter-frame feature reconstruction (IFR) | Accel · CamVid test, 1/30 labeled data | mIoU: 42.37 -> 49.50 | Helped |
| Add IFR | DFF · Cityscapes val, 1/30 labeled data | mIoU: +5.78 | Helped |
| Add IFR | DAVSS · Cityscapes val, 1/30 labeled data | mIoU: +5.46 | Helped |
| Add labeled-video feature reconstruction loss (ablation) | IFR · Cityscapes, 1/30 labeled data | mIoU: +2.45 | Helped |
| Add unlabeled-video feature reconstruction loss (ablation) | IFR · Cityscapes, 1/30 labeled data | mIoU: +3.13 | Helped |
| Add reconstruction on strongly augmented frames (ablation) | IFR · Cityscapes, 1/30 labeled data | mIoU: +2.98 | Helped |
| Combine labeled- and unlabeled-video reconstruction (ablation) | IFR · Cityscapes, 1/30 labeled data | mIoU: +3.83 | Helped |
| Combine labeled and unlabeled reconstruction with strong augmentation (ablation) | IFR · Cityscapes, 1/30 labeled data | mIoU: 43.68 -> 48.40 | Helped |
| Add IFR | Accel on Cityscapes-VPS · Training frame ID 20 | accuracy: 81.5 -> 76.5 | Hurt |
| Add IFR | Accel on Cityscapes-VPS · Training frame ID 5 | accuracy: 60.6 -> 66.8 | Helped |
| Add IFR | Accel on Cityscapes-VPS · Validation frame ID 20 | accuracy: 49.8 -> 53.9 | Helped |
Closest papers by meaning
- Simultaneously Short- and Long-Term Temporal Modeling for Semi-Supervised Video Semantic Segmentation (CVPR 2023 · similarity 0.89)
- Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video Segmentation (CVPR 2024 · similarity 0.87)
- AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation (CVPR 2024 · similarity 0.86)
- Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation (AAAI 2024 · similarity 0.86)
- VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models (CVPR 2025 · similarity 0.86)
- Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity (CVPR 2025 · 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.