Research map / Detection and segmentation / CNN features
RFC-Net: Learning High Resolution Global Features for Medical Image Segmentation on a Computational Budget (Student Abstract)
Read the paperCheck 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 |
|---|---|---|---|
| Use the three-way tree with receptive fields k=3,5,7 rather than k=3 throughout (ablation) | RFC-Net · Kvasir | mIOU (%): 79.15 -> 81.31 | Helped |
| Use the three-way tree with receptive fields k=3,5,7 rather than k=3 throughout (ablation) | RFC-Net · GlaS | mIOU (%): 75.34 -> 77.88 | Helped |
| Use the three-way tree with receptive fields k=3,5,7 rather than k=3 throughout (ablation) | RFC-Net · CVC-ClinicDB | mIOU (%): 83.34 -> 85.90 | Helped |
| Use distinct kernels k=3,5 in the two-way tree rather than k=3 for both (ablation) | RFC-Net · Kvasir | mIOU (%): 73.24 -> 76.41 | Helped |
| Use distinct kernels k=3,5 in the two-way tree rather than k=3 for both (ablation) | RFC-Net · GlaS | mIOU (%): 66.17 -> 75.49 | Helped |
| Use distinct kernels k=3,5 in the two-way tree rather than k=3 for both (ablation) | RFC-Net · CVC-ClinicDB | mIOU (%): 77.68 -> 79.51 | Helped |
| Use RFC-Netᵃ instead of ResUNet | RFC-Net · Kvasir | mIOU (%): 77.77 -> 81.31 | Helped |
| Use RFC-Netᵃ instead of ResUNet | RFC-Net · GlaS | mIOU (%): 85.67 -> 77.88 | Hurt |
| Use RFC-Netᵃ instead of ResUNet | RFC-Net · CVC-ClinicDB | mIOU (%): 81.33 -> 85.90 | Helped |
Closest papers by meaning
- nnWNet: Rethinking the Use of Transformers in Biomedical Image Segmentation and Calling for a Unified Evaluation Benchmark (CVPR 2025 · similarity 0.86)
- Upping the Game: How 2D U-Net Skip Connections Flip 3D Segmentation (NeurIPS 2024 · similarity 0.86)
- Densely Connected Multi-Dilated Convolutional Networks for Dense Prediction Tasks (CVPR 2021 · similarity 0.86)
- Rethinking U-Net: Task-Adaptive Mixture of Skip Connections for Enhanced Medical Image Segmentation (AAAI 2025 · similarity 0.85)
- U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation (AAAI 2025 · similarity 0.84)
- FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks (ICML 2025 · similarity 0.84)
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.