Research map / Video / Video segmentation and tracking
Domain Adaptive Video Segmentation via Temporal Consistency Regularization
Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu
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 spatial adversarial alignment (ablation) | Source only · VIPER -> Cityscapes-Seq | mIoU: 37.1 -> 41.6 | Improved |
| add spatial-temporal adversarial alignment (ablation) | Source only · VIPER -> Cityscapes-Seq | mIoU: 37.1 -> 43.7 | Improved |
| add spatial alignment on top of spatial-temporal alignment (joint training) (ablation) | STA · VIPER -> Cityscapes-Seq | mIoU: 43.7 -> 44.2 | Improved |
| add weight discrepancy loss between STA and SA discriminators (ablation) | JT · VIPER -> Cityscapes-Seq | mIoU: 44.2 -> 46.5 | Improved |
| add intra-domain TCR to cross-domain TCR (ablation) | C-TCR · VIPER -> Cityscapes-Seq | mIoU: 46.5 -> 47.8 | Improved |
| add cross-domain TCR to intra-domain TCR (ablation) | I-TCR · VIPER -> Cityscapes-Seq | mIoU: 45.9 -> 47.8 | Improved |
| add intra-domain TCR alone to source-only training (ablation) | Source only · VIPER -> Cityscapes-Seq | mIoU: 37.1 -> 45.9 | Improved |
| plug DA-VSN into FDA | FDA · VIPER -> Cityscapes-Seq | mIoU: 44.4 -> 48.5 (+4.1) | Improved |
| plug DA-VSN into IDA | IDA · VIPER -> Cityscapes-Seq | mIoU: 42.0 -> 49.9 (+7.9) | Improved |
| plug DA-VSN into CBST | CBST · VIPER -> Cityscapes-Seq | mIoU: 41.7 -> 50.2 (+8.5) | Improved |
| plug DA-VSN into CRST | CRST · VIPER -> Cityscapes-Seq | mIoU: 42.4 -> 51.3 (+8.9) | Improved |
| use NetWarp video architecture with DA-VSN | NetWarp · VIPER -> Cityscapes-Seq | mIoU: 36.5 -> 47.2 (+10.7) | Improved |
Closest papers by meaning
- Pay Attention to Target: Relation-Aware Temporal Consistency for Domain Adaptive Video Semantic Segmentation (AAAI 2024 · similarity 0.91)
- Is It Necessary to Transfer Temporal Knowledge for Domain Adaptive Video Semantic Segmentation? (ECCV 2022 · similarity 0.91)
- Domain Adaptive Video Segmentation via Temporal Pseudo Supervision (ECCV 2022 · similarity 0.90)
- Unified Domain Adaptive Semantic Segmentation (TPAMI 2025 · similarity 0.87)
- Hybrid Instance-Aware Temporal Fusion for Online Video Instance Segmentation (AAAI 2022 · similarity 0.87)
- Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation (CVPR 2026 · similarity 0.87)
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.
