Research map / Detection and segmentation / Open-set and few-shot detection
MSeg: A Composite Dataset for Multi-Domain 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 |
|---|---|---|---|
| reconcile taxonomies across training datasets and train on their composite (ablation) | MSeg semantic segmentation model · MSeg test datasets | harmonic mean mIoU: 33.1 -> 59.2 | Helped |
| add manually relabeled masks for split classes (ablation) | MSeg semantic segmentation model · MSeg test datasets | harmonic mean mIoU: 57.6 -> 59.2 | Helped |
| train on reconciled multi-domain data rather than the best individually trained dataset | MSeg semantic segmentation model · MSeg test datasets | harmonic mean mIoU: 45.8 -> 59.2 | Helped |
| train on reconciled multi-domain data rather than the best individually trained dataset | MSeg semantic segmentation model · MSeg training datasets | harmonic mean mIoU: 32.4 -> 57.1 | Helped |
| use 480p rather than 1080p resolution (ablation) | MSeg-3m semantic segmentation model · MSeg test datasets | harmonic mean mIoU: 59.8 -> 61.2 | Helped |
| use 1080p rather than 480p resolution (ablation) | MSeg-3m semantic segmentation model · MSeg training datasets | harmonic mean mIoU: 58.5 -> 58.8 | Helped |
| use 1080p rather than 480p resolution (ablation) | MSeg-3m panoptic segmentation model · MSeg training datasets | PQ: 35.7 -> 38.8; 32.7 -> 33.7; 14.0 -> 14.9; 47.5 -> 45.0; 49.5 -> 51.1 | Mixed |
| use a taxonomy matched to Mapillary-46 rather than scoring against Mapillary-65 (ablation) | MSeg1080_RVC · Mapillary Vistas | mIoU: 34.19 -> 48.31 | Helped |
Closest papers by meaning
- UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior (NeurIPS 2024 · similarity 0.89)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.88)
- RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation (NeurIPS 2025 · similarity 0.88)
- Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation (CVPR 2025 · similarity 0.88)
- OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation (NeurIPS 2025 · similarity 0.88)
- Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training (AAAI 2024 · 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.