Research map / Label-efficient and robust learning / Recognition and long-tail
Quantum-Inspired Spectral-Spatial Pyramid Network for Hyperspectral Image Classification
Jie Zhang, Yongshan Zhang, Yicong Zhou
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 jointly predicted spatial-spectral phases instead of using no phase (ablation) | QSSPN-2 · Indian Pines | OA: 86.86 -> 92.66 | Improved |
| Add jointly predicted spatial-spectral phases instead of using no phase (ablation) | QSSPN-2 · Indian Pines | κ: 85.10 -> 91.68 | Improved |
| Add spectral phase information to spatial-only phases (ablation) | QSSPN-2 · Indian Pines | OA: 89.18 -> 92.66 | Improved |
| Add spatial phase information to spectral-only phases (ablation) | QSSPN-2 · Indian Pines | OA: 88.66 -> 92.66 | Improved |
| Increase one-block output channels from 10 to 30 (ablation) | QSSPN-1 · Indian Pines | OA: 82.72 -> 90.36 | Improved |
| Increase one-block output channels from 30 to 50 (ablation) | QSSPN-1 · Indian Pines | OA: 90.36 -> 91.63 | Improved |
| Add a second QSSN block rather than use one block, with 30 output channels (ablation) | QSSPN · Indian Pines | OA: 90.36 -> 91.93 | Improved |
| Add a third QSSN block rather than use two blocks, with 30 output channels (ablation) | QSSPN · Indian Pines | OA: 91.93 -> 92.93 | Improved |
| Use a deeper pyramid model (ablation) | QSSPN · Indian Pines | OA | Improved |
| Use a deeper pyramid model (ablation) | QSSPN · Salinas | OA | Improved |
| Use a 9-pixel patch rather than an 11-pixel patch (ablation) | QSSPN-2 · Indian Pines | OA | Improved |
| Use jointly fused spatial-spectral information rather than separately aggregating it | QSSPN · Indian Pines | AA: 89.99 -> 96.40 | Improved |
Closest papers by meaning
- QuCNet: Quantum Deep Learning Driven Multi-Circuit Network for Remote Sensing Image Classification (CVPR 2026 · similarity 0.87)
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.84)
- Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution (CVPR 2018 · similarity 0.84)
- QKSAN: A Quantum Kernel Self-Attention Network (TPAMI 2024 · similarity 0.84)
- Uncertainty-aware Graph-based Hyperspectral Image Classification (ICLR 2024 · similarity 0.84)
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.82)
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.
