Research map / Label-efficient and robust learning / Recognition and long-tail
Representative-Discriminative Learning for Open-set Land Cover Classification of Satellite Imagery
Razieh Kaviani Baghbaderani, Ying Qu, Hairong Qi, Craig Stutts
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 Dirichlet-based encoder to AE+CLS (ablation) | AE+CLS · Pavia University (openness 2.99%) | AUC (open-set detection): 0.586 -> 0.714 | Improved |
| add Dirichlet-based encoder to AE+CLS (ablation) | AE+CLS · Indian Pines (openness 1.63%) | AUC (open-set detection): 0.669 -> 0.681 | Improved |
| add Dirichlet-based encoder to AE+CLS (ablation) | AE+CLS · Pavia Center (openness 2.99%) | AUC (open-set detection): 0.757 -> 0.927 | Improved |
| add closed-set embedding layer with sparsity constraint to AE+CLS+Dirichlet (ablation) | AE+CLS+Dirichlet · Pavia University (openness 2.99%) | AUC (open-set detection): 0.714 -> 0.773 | Improved |
| add closed-set embedding layer with sparsity constraint to AE+CLS+Dirichlet (ablation) | AE+CLS+Dirichlet · Indian Pines (openness 1.63%) | AUC (open-set detection): 0.681 -> 0.802 | Improved |
| add closed-set embedding layer with sparsity constraint to AE+CLS+Dirichlet (ablation) | AE+CLS+Dirichlet · Pavia Center (openness 2.99%) | AUC (open-set detection): 0.927 -> 0.963 | Improved |
| move open-set recognition from image space to embedding space (no sparsity) (ablation) | AE+CLS+Dirichlet · Pavia University (openness 2.99%) averaged | AUC (open-set detection): 0.71 -> 0.77 | Improved |
| move open-set recognition from image space to embedding space (no sparsity) (ablation) | AE+CLS · Pavia University (openness 2.99%) averaged | AUC (open-set detection): 0.59 -> 0.74 | Improved |
| perform open-set recognition in embedding space without sparsity constraint on z_F (ablation) | embedding space open-set · Pavia University | AUC (open-set detection) | Hurt |
| use RDOSR in embedding space instead of image-space methods | SoftMax · TinyImageNet (openness 57.35%) | AUC (open-set detection): 0.577 -> 0.752 | Improved |
| use RDOSR instead of GDOSR | GDOSR · CIFAR10 (openness 13.39%) | AUC (open-set detection): 0.807 -> 0.744 | Hurt |
Closest papers by meaning
- InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition (NeurIPS 2025 · similarity 0.86)
- Learning De-Biased Representations for Remote-Sensing Imagery (NeurIPS 2024 · similarity 0.84)
- SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing (AAAI 2024 · similarity 0.84)
- Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation (AAAI 2025 · similarity 0.84)
- Scale-aware Recognition in Satellite Images under Resource Constraints (ICLR 2025 · similarity 0.84)
- DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications (ICML 2025 · 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.
