Research map / Label-efficient and robust learning / Domain adaptation and generalization
Spectral Property-Driven Data Augmentation for Hyperspectral Single-Source Domain Generalization
Taiqin Chen, Yifeng Wang, Xiaochen Feng, Zhilin Zhu, Hao Sha, Yingjian Li, Yongbing Zhang
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 CASM to SPDDA (no SF, SC) (ablation) | SPDDA · Houston | OA (%): 74.73 -> 76.95 | Improved |
| add L_SF with fixed mixer (ablation) | SPDDA · Houston | OA (%): 74.73 -> 70.93 | Hurt |
| add L_SC with fixed mixer (ablation) | SPDDA · Houston | OA (%): 74.73 -> 72.23 | Hurt |
| add L_SF to CASM (ablation) | SPDDA · Houston | OA (%): 76.95 -> 77.87 | Improved |
| add L_SC to CASM (ablation) | SPDDA · Houston | OA (%): 76.95 -> 75.94 | Hurt |
| add L_SC to CASM + L_SF (full method) (ablation) | SPDDA · Houston | OA (%): 77.87 -> 78.60 | Improved |
| add CASM to L_SF + L_SC (ablation) | SPDDA · Houston | OA (%): 71.26 -> 78.60 | Improved |
| use adaptive lambda instead of fixed 1.0 (ablation) | SPDDA · Houston | OA (%): 72.05 -> 78.60 | Improved |
| use adaptive lambda instead of fixed 0.1 (ablation) | SPDDA · Houston | OA (%): 75.19 -> 78.60 | Improved |
| use adaptive lambda instead of two-stage schedule by epoch (ablation) | SPDDA · Houston | OA (%): 76.15 -> 78.60 | Improved |
| use adaptive lambda instead of two-stage schedule by L_SF (ablation) | SPDDA · Houston | OA (%): 75.62 -> 78.60 | Improved |
| replace S2ECNet with SPDDA on HyRank | hyperspectral SDG · HyRank | OA (%): 60.21 -> 60.70 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StyDeSty — StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization (ICML 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Skipping Domain Shifts: Domain Memory Retention Enhanced Hyperspectral Single-Source Domain Generalization (NeurIPS 2026 · similarity 0.90)
- LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift (NeurIPS 2026 · similarity 0.86)
- OneHSI: A Unified Hyperspectral Foundation Model with Physical Consistency (ECCV 2026 · similarity 0.86)
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.86)
- Unsupervised Adaptation Learning for Hyperspectral Imagery Super-Resolution (CVPR 2020 · similarity 0.86)
- Local Precise Refinement: A Dual-Gated Mixture-of-Experts for Enhancing Foundation Model Generalization against Spectral Shifts (CVPR 2026 · 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.
