Research map / Label-efficient and robust learning / Recognition and long-tail
Dual-stage Hyperspectral Image Classification Model with Spectral Supertoken
Peifu Liu, Tingfa Xu, Jie Wang, Huan Chen, Huiyan Bai, Jianan Li
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 semantic features to supertoken clustering (ablation) | DSTC-R · WHU-OHS | CF1: 0.669 -> 0.717 | Improved |
| add first-order spectral derivative features (ablation) | DSTC-R · WHU-OHS | CF1: 0.717 -> 0.721 | Improved |
| add second-order spectral derivative features (ablation) | DSTC-R · WHU-OHS | CF1: 0.721 -> 0.713 | Hurt |
| use class-proportion soft labels instead of hard labels (ablation) | DSTC-R · WHU-OHS | CF1: 0.443 -> 0.721 | Improved |
| use soft labels on supertokens instead of dense pixel-level CE (ablation) | DSTC-R · WHU-OHS | CF1: 0.699 -> 0.721 | Improved |
| increase centroids per segment from 1 to 4 (ablation) | DSTC-R · WHU-OHS | CF1: 0.697 -> 0.721 | Improved |
| increase centroids per segment from 4 to 16 (ablation) | DSTC-R · WHU-OHS | CF1: 0.721 -> 0.685 | Hurt |
| increase crop factor F from 4 to 16 (ablation) | DSTC-R · WHU-OHS | CF1: 0.698 -> 0.721 | Improved |
| use DSTC dual-stage supertoken model versus prior methods on large dataset | WHU-OHS · WHU-OHS | CF1: 0.683 -> 0.723 | Improved |
| use DSTC on small patch-based datasets vs CVSSN | IP, KSC, UP · IP / KSC / UP | OA: IP 0.9827 -> 0.9875; KSC 0.9870 -> 0.9860; UP 0.9988 -> 0.9982 | Mixed |
Closest papers by meaning
- SSDCN: Spatial-Spectral Dual-Clustering-based Network for Hyperspectral Image Super-resolution (ICML 2026 · similarity 0.87)
- LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift (NeurIPS 2026 · similarity 0.84)
- S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data (CVPR 2024 · similarity 0.84)
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.83)
- Hyperspectral Image Reconstruction via Combinatorial Embedding of Cross-Channel Spatio-Spectral Clues (AAAI 2024 · similarity 0.83)
- HetSSNet: Spatial-Spectral Heterogeneous Graph Learning Network for Panchromatic and Multispectral Images Fusion (ICML 2025 · 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.
