Research map / Architectures and efficiency / Attention and transformers
S2M-Net: Spectral-Spatial Mixing with Morphology-Aware Adaptive Loss for Medical Image Segmentation
Sanaullah Chowdhury, Lameya Sabrin
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 Spectral-Selective Token Mixing (SSTM) (ablation) | S2M-Net · Kvasir-SEG | Dice (%): 88.45 -> 96.05 | Improved |
| add Boundary-Focused Decoder (ablation) | S2M-Net · Kvasir-SEG | Dice (%): 89.87 -> 96.05 | Improved |
| add MRF-SE local block (ablation) | S2M-Net · Kvasir-SEG | Dice (%): 89.23 -> 96.05 | Improved |
| add boundary loss component to MASL (ablation) | S2M-Net · Kvasir-SEG | Dice (%): 87.96 -> 96.05 | Improved |
| add core loss component to MASL (ablation) | S2M-Net · GlaS | Dice (%): 77.32 -> 93.83 | Improved |
| add texture loss component to MASL (ablation) | S2M-Net · GlaS | Dice (%): 88.67 -> 93.83 | Improved |
| use learned morphology-adaptive weights instead of fixed weights (ablation) | MASL · Kvasir-SEG | Dice (%): 88.92 -> 96.05 | Improved |
| add per-sample morphology modulation (ablation) | MASL · Kvasir-SEG | Dice (%): 89.37 -> 96.05 | Improved |
| increase spectral truncation K from 32 to 64 (ablation) | SSTM · PH2 | Dice (%): 96.67 -> 93.11 | Hurt |
| increase spectral truncation K from 16 to 32 (ablation) | SSTM · Kvasir-SEG | Dice (%): 89.87 -> 96.05 | Improved |
| increase spectral truncation K from 32 to 48 (ablation) | SSTM · Kvasir-SEG | Dice (%): 96.05 -> 95.98 | No clear effect |
| train S2M-Net with MASL instead of Dice+CE (ablation) | S2M-Net · EndoVis-2017 multiclass | Dice (%): 78.91 -> 83.43 | Improved |
Closest papers by meaning
- S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging (AAAI 2025 · similarity 0.87)
- Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding (CVPR 2024 · similarity 0.86)
- A Unified Degradation-Robust Approach to SSL and UDA for 3D Medical Images (AAAI 2025 · similarity 0.86)
- FAMNet: Frequency-aware Matching Network for Cross-domain Few-shot Medical Image Segmentation (AAAI 2025 · similarity 0.86)
- LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation (NeurIPS 2025 · similarity 0.86)
- Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains (NeurIPS 2025 · 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.
