Research map / Label-efficient and robust learning / Domain adaptation and generalization
Anchor-Guided Discriminative Subspace Alignment and Clustering for Cross-Scene Hyperspectral Imagery
Yongshan Zhang, Zixuan Zhang, Xinxin Wang, Lefei Zhang, Zhihua Cai
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 APGL anchor graph clustering instead of k-means (no DCSA) (ablation) | ADSAC · Cross-scene HSI clustering H13→H18 | ACC: 0.3999 -> 0.4638 | Improved |
| add APGL instead of k-means (no DCSA) (ablation) | ADSAC · Cross-scene HSI clustering PU→PC | ACC: 0.5633 -> 0.7008 | Improved |
| add DCSA subspace alignment (k-means source labels) (ablation) | ADSAC · Cross-scene HSI clustering H13→H18 | ACC: 0.3999 -> 0.5335 | Improved |
| add DCSA subspace alignment (k-means source labels) (ablation) | ADSAC · Cross-scene HSI clustering PU→PC | ACC: 0.5633 -> 0.6430 | Improved |
| add DCSA on top of APGL (full model vs APGL only) (ablation) | ADSAC · Cross-scene HSI clustering H13→H18 | ACC: 0.4638 -> 0.8688 | Improved |
| add DCSA on top of APGL (full model vs APGL only) (ablation) | ADSAC · Cross-scene HSI clustering PU→PC | ACC: 0.7008 -> 0.8341 | Improved |
| add APGL on top of DCSA (full model vs DCSA only) (ablation) | ADSAC · Cross-scene HSI clustering Lo→Di | ACC: 0.6972 -> 0.7723 | Improved |
| use APGL instead of S3AGC for source clustering (ablation) | ADSAC · Cross-scene HSI clustering H13→H18 | ACC: 0.6687 -> 0.8688 | Improved |
| use APGL instead of SAPC for source clustering (ablation) | ADSAC · Cross-scene HSI clustering Di→Lo | ACC: 0.7930 -> 0.8379 | Improved |
| use APGL instead of S3AGC for source clustering (ablation) | ADSAC · Cross-scene HSI clustering H18→H13 | ACC: 0.8497 -> 0.8680 | Improved |
| ADSAC vs strongest baseline on cross-scene clustering | ADSAC · Cross-scene HSI clustering PC→PU | ACC: 0.6285 -> 0.7286 | Improved |
| ADSAC vs strongest baseline on cross-scene clustering | ADSAC · Cross-scene HSI clustering H13→H18 | ACC: 0.6149 -> 0.8688 | Improved |
Closest papers by meaning
- Context-Aware Joint Alignment for Cross-Scene Hyperspectral Image Classification (ECCV 2026 · similarity 0.90)
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.85)
- LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift (NeurIPS 2026 · similarity 0.84)
- Solving Spectrum Unmixing as a Multi-Task Bayesian Inverse Problem with Latent Factors for Endmember Variability (AAAI 2024 · similarity 0.83)
- Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization (CVPR 2024 · similarity 0.83)
- Hyperspectral Image Reconstruction via Combinatorial Embedding of Cross-Channel Spatio-Spectral Clues (AAAI 2024 · 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.
