Research map / Detection and segmentation / CNN features
Orientation-Aware Semantic Segmentation on Icosahedron Spheres
Chao Zhang, Stephan Liwicki, William Smith, Roberto Cipolla
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 |
|---|---|---|---|
| retrain transferred weights 10 epochs instead of 1 (ablation) | HexUNet-T · Omni-SYNTHIA r=6 | segmentation score (unnamed in supplement): 29.4 -> 36.7 | Improved |
| retrain transferred weights 10 epochs instead of 1 (ablation) | HexUNet-T · Omni-SYNTHIA r=7 | segmentation score (unnamed in supplement): 30.3 -> 38.0 | Improved |
| retrain transferred weights 10 epochs instead of 1 (ablation) | HexUNet-T · Omni-SYNTHIA r=8 | segmentation score (unnamed in supplement): 35.9 -> 45.3 | Improved |
| transfer perspective U-Net weights and refine 10 epochs vs perspective U-Net (ablation) | HexUNet-T · Omni-SYNTHIA r=8 | segmentation score (unnamed in supplement): 43.8 -> 45.3 | Improved |
| transfer perspective U-Net weights and refine 10 epochs vs perspective U-Net (ablation) | HexUNet-T · Omni-SYNTHIA r=6 | segmentation score (unnamed in supplement): 38.8 -> 36.7 | Hurt |
| train spherical HexUNet for 500 epochs vs transferred 10 epochs (ablation) | HexUNet-T · Omni-SYNTHIA r=8 | segmentation score (unnamed in supplement): 45.3 -> 47.1 | Improved |
Closest papers by meaning
- Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment (ICCV 2025 · similarity 0.83)
- Deep Hierarchical Learning for 3D Semantic Segmentation (IJCV 2025 · similarity 0.81)
- PanSt3R: Multi-view Consistent Panoptic Segmentation (ICCV 2025 · similarity 0.81)
- SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes (CVPR 2025 · similarity 0.80)
- AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation (NeurIPS 2026 · similarity 0.80)
- LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds (CVPR 2025 · similarity 0.79)
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.
