Research map / Detection and segmentation / CNN features
Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening
Junfeng Li, Wenyang Zhou, Xueheng Li, Xuanhua He, Jianhou Gan, Wenqi Ren
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 average (global) token (ablation) | MTRWKV with momentum · WorldView-II | PSNR: 42.0364 -> 42.1360 | Improved |
| add average (global) token (ablation) | MTRWKV with momentum · GaoFen2 | PSNR: 47.5367 -> 47.6217 | Improved |
| add learnable register token (ablation) | MTRWKV with momentum and average token · WorldView-II | PSNR: 42.1360 -> 42.2192 | Improved |
| add learnable register token (ablation) | MTRWKV with momentum and average token · GaoFen2 | PSNR: 47.6217 -> 47.6681 | Improved |
| add semantic prototype tokens (ablation) | MTRWKV with momentum and avg+learn tokens · WorldView-II | PSNR: 42.2192 -> 42.3750 | Improved |
| add semantic prototype tokens (ablation) | MTRWKV with momentum and avg+learn tokens · GaoFen2 | PSNR: 47.6681 -> 47.8941 | Improved |
| add WKV momentum (ablation) | MTRWKV with all tokens and prototype · WorldView-II | PSNR: 42.2800 -> 42.3750 | Improved |
| add WKV momentum (ablation) | MTRWKV with all tokens and prototype · GaoFen2 | ERGAS: 0.5186 -> 0.5115 | Improved |
| add prototype learning without momentum (ablation) | MTRWKV with all tokens · WorldView-II | PSNR: 42.2192 -> 42.2800 | No clear effect |
| use full method instead of strongest baseline SFINet | MTRWKV · WorldView-II | PSNR: 41.7244 -> 42.3751 | Improved |
| use full method instead of strongest baseline SFINet | MTRWKV · WorldView-III | PSNR: 30.5971 -> 31.3113 | Improved |
| use full method instead of SFINet | MTRWKV · GaoFen2 | SSIM: 0.9901 -> 0.9901 | No clear effect |
Closest papers by meaning
- Deep Adaptive Unfolded Network via Spatial Morphology Stripping and Spectral Filtration for Pan-sharpening (ICCV 2025 · similarity 0.85)
- SWIFT: Spatial-Window Integrated Frequency-aware Token Pruning for Efficient MLLMs on Edge Devices (ECCV 2026 · similarity 0.85)
- IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning (ICLR 2026 · similarity 0.84)
- Instruction-Guided Cross-Modal Clustering for Training-Free Visual Token Pruning in Vision-Language Models (AAAI 2026 · similarity 0.84)
- U-Know-DiffPAN: An Uncertainty-aware Knowledge Distillation Diffusion Framework with Details Enhancement for PAN-Sharpening (CVPR 2025 · similarity 0.84)
- Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid (ICLR 2025 · similarity 0.83)
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.
