Research map / Video / Video segmentation and tracking
Efficient Semantic Video Segmentation with Per-frame Inference
Yifan Liu, Chunhua Shen, Changqian Yu, Jingdong Wang
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 single-frame distillation (SF) (ablation) | PSPNet18 baseline · Cityscapes val (PSPNet18) | mIoU: 69.79 -> 70.85 | Improved |
| add pair-wise-frame distillation (PF) (ablation) | PSPNet18 baseline · Cityscapes val (PSPNet18) | temporal consistency: 68.50 -> 70.10 | Improved |
| add multi-frame distillation (MF) (ablation) | PSPNet18 baseline · Cityscapes val (PSPNet18) | temporal consistency: 68.50 -> 69.78 | Improved |
| add temporal loss (TL) (ablation) | PSPNet18 baseline · Cityscapes val (PSPNet18) | temporal consistency: 68.50 -> 70.46 | Improved |
| add temporal loss (TL) (ablation) | PSPNet18 baseline · Cityscapes val (PSPNet18) | mIoU: 69.79 -> 70.67 | Improved |
| add SF to PF+MF distillation (ablation) | PF+MF · Cityscapes val (PSPNet18) | temporal consistency: 70.21 -> 69.99 | Hurt |
| add SF to PF+MF distillation (ablation) | PF+MF · Cityscapes val (PSPNet18) | mIoU: 71.16 -> 72.01 | Improved |
| add temporal loss to all distillation terms (ablation) | SF+PF+MF · Cityscapes val (PSPNet18) | mIoU: 72.01 -> 73.06 | Improved |
| add temporal loss to all distillation terms (ablation) | SF+PF+MF · Cityscapes val (PSPNet18) | temporal consistency: 69.99 -> 70.56 | Improved |
| add random sample policy to temporal loss (ablation) | PSPNet18 + TL · Cityscapes val (PSPNet18) | mIoU: 70.04 -> 70.67 | Improved |
| add random sample policy to distillation terms (ablation) | PSPNet18 + Dis · Cityscapes val (PSPNet18) | mIoU: 71.24 -> 72.01 | Improved |
| add random sample policy to all terms (ablation) | PSPNet18 + ALL · Cityscapes val (PSPNet18) | mIoU: 72.87 -> 73.06 | Improved |
Closest papers by meaning
- Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation (CVPR 2026 · similarity 0.91)
- Exploiting Temporal State Space Sharing for Video Semantic Segmentation (CVPR 2025 · similarity 0.90)
- Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation (AAAI 2024 · similarity 0.88)
- Pay Attention to Target: Relation-Aware Temporal Consistency for Domain Adaptive Video Semantic Segmentation (AAAI 2024 · similarity 0.88)
- The Devil is in Temporal Token: High Quality Video Reasoning Segmentation (CVPR 2025 · similarity 0.88)
- VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models (CVPR 2025 · similarity 0.88)
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.
