Research map / Detection and segmentation / Open-set and few-shot detection
Transferring and Regularizing Prediction for Semantic Segmentation
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 patch-based consistency regularization (ablation) | FCN_adv · GTA5 → Cityscapes | mIoU: 47.2 -> 49.0 | Helped |
| Add cluster-based consistency regularization (ablation) | FCN_adv+PCR · GTA5 → Cityscapes | mIoU: 49.0 -> 49.6 | Helped |
| Add spatial logic regularization (ablation) | FCN_adv+PCR+CCR · GTA5 → Cityscapes | mIoU: 49.6 -> 50.4 | Helped |
| Increase state updates from one to three (ablation) | RPT · GTA5 → Cityscapes | mIoU: 50.4 -> 52.6 | Helped |
| Add RPT^3 to FCN_adv | FCN_adv · GTA5 → Cityscapes | mIoU: 47.2 -> 52.6 | Helped |
| Add a multi-scale scheme to FCN_adv+RPT^3 (ablation) | FCN_adv+RPT^3 · GTA5 → Cityscapes | mIoU: 52.6 -> 53.2 | Helped |
| Add RPT^3 and multi-scale scheme | FCN_adv · SYNTHIA → Cityscapes | mIoU@16: 46.7 -> 51.7 | Helped |
| Add RPT^3 and multi-scale scheme | FCN_adv · SYNTHIA → Cityscapes | mIoU@13: 53.3 -> 59.5 | Helped |
Closest papers by meaning
- Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection (CVPR 2019 · similarity 0.90)
- ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes (CVPR 2018 · similarity 0.89)
- Transferable Semi-Supervised Semantic Segmentation (AAAI 2018 · similarity 0.89)
- Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach (CVPR 2019 · similarity 0.89)
- Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.87)
- MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation (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.