Research map / Detection and segmentation / CNN features
Decoding with Structured Awareness: Integrating Directional, Frequency-Spatial, and Structural Attention for Medical Image Segmentation
Fan Zhang, Zhiwei Gu, Hua Wang
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 ACFA module (ablation) | PVTv2 baseline decoder · Synapse | DSC: 81.35 -> 82.04 | Improved |
| add ACFA module (ablation) | PVTv2 baseline decoder · Synapse | HD95: 20.42 -> 21.46 | Hurt |
| add TFFA module on top of ACFA (ablation) | Baseline+ACFA · Synapse | DSC / HD95: 82.04 -> 83.23 DSC; 21.46 -> 16.72 HD95 | Improved |
| add SMMM on top of ACFA+TFFA (ablation) | Baseline+ACFA+TFFA · Synapse | DSC: 83.23 -> 83.92 | Improved |
| add SMMM on top of ACFA+TFFA (ablation) | Baseline+ACFA+TFFA · Synapse | HD95: 16.72 -> 18.91 | Hurt |
| add ACFA module (ablation) | PVTv2 baseline decoder · ISIC 2017 | DSC: 85.95 -> 87.82 | Improved |
| add TFFA module on top of ACFA (ablation) | Baseline+ACFA · ISIC 2017 | DSC: 87.82 -> 89.15 | Improved |
| add SMMM on top of ACFA+TFFA (ablation) | Baseline+ACFA+TFFA · ISIC 2017 | DSC: 89.15 -> 91.40 | Improved |
| add ACFA module (ablation) | PVTv2 baseline decoder · ISIC 2017 | specificity / accuracy: 98.96 -> 98.16 SP; 96.05 -> 95.92 ACC | Hurt |
| add Fourier branch to TFFA (ablation) | TFFA · ISIC 2018 | DSC: 90.32 -> 90.48 | Improved |
| add Mexican Hat wavelet to TFFA (ablation) | TFFA + Fourier · ISIC 2018 | DSC: 90.48 -> 90.57 | Improved |
| add DoG wavelet to TFFA (ablation) | TFFA + Fourier + Mexican Hat · ISIC 2018 | DSC: 90.57 -> 90.71 | Improved |
Closest papers by meaning
- EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation (CVPR 2024 · similarity 0.87)
- Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding (CVPR 2024 · similarity 0.87)
- Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention (CVPR 2025 · similarity 0.86)
- ConDSeg: A General Medical Image Segmentation Framework via Contrast-Driven Feature Enhancement (AAAI 2025 · similarity 0.85)
- MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention (NeurIPS 2026 · similarity 0.84)
- EffiDec3D: An Optimized Decoder for High-Performance and Efficient 3D Medical Image Segmentation (CVPR 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.
