Research map / Label-efficient and robust learning / Domain adaptation and generalization
Skipping Domain Shifts: Domain Memory Retention Enhanced Hyperspectral Single-Source Domain Generalization
Taiqin Chen, Hao Sha, Xiaochen Feng, Chunyu Chen, XiangYu Chen, Ke Chen, yongbing zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a domain memory retention approach for hyperspectral single-source domain generalization to handle cross-scene domain shifts from one source domain.
Problem
Hyperspectral single-source domain generalization: training a robust HSI classifier using only one source domain that generalizes to unseen cross-scene domains under domain shift.
Approach
Existing approaches use data augmentation to broaden decision boundaries or style transfer for test-time alignment, which the abstract says fail to completely bridge the domain gap; this paper instead retains domain memory to skip domain shifts (details not stated in the abstract).
Closest papers by meaning
- Spectral Property-Driven Data Augmentation for Hyperspectral Single-Source Domain Generalization (AAAI 2026 · similarity 0.90)
- Context-Aware Joint Alignment for Cross-Scene Hyperspectral Image Classification (ECCV 2026 · similarity 0.87)
- Degradation-Aware Metric Prompting for Hyperspectral Image Restoration (ICML 2026 · similarity 0.87)
- Parameter Efficient Self-Supervised Geospatial Domain Adaptation (CVPR 2024 · similarity 0.85)
- LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift (NeurIPS 2026 · similarity 0.84)
- HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery (CVPR 2025 · similarity 0.84)
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.
