Research map / Detection and segmentation / Open-set and few-shot detection
Sparse and Complete Latent Organization for Geospatial Semantic Segmentation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use SCO instead of PFSegNet | ResNet-50 segmentation on iSAID · iSAID | mIoU (%): 66.9% to 69.1% | Helped |
| add attraction loss Lattr (ablation) | FarSeg baseline · iSAID | mIoU (%): 63.7 -> 65.1 | Helped |
| add local repulsion loss Llocal_rep (ablation) | FarSeg baseline · iSAID | mIoU (%): 63.7 -> 64.8 | Helped |
| combine attraction and local repulsion losses (ablation) | FarSeg baseline · iSAID | mIoU (%): 63.7 -> 65.4 | Helped |
| add global repulsion loss Lglobal_rep (ablation) | local prototypical contrastive loss · iSAID | mIoU (%): 65.4 -> 67.8 | Helped |
| add foreground-background repulsion loss Lfb_rep (ablation) | local prototypical contrastive loss · iSAID | mIoU (%): 65.4 -> 67.4 | Helped |
| add global repulsion and foreground-background repulsion losses (ablation) | local prototypical contrastive loss · iSAID | mIoU (%): 65.4 -> 69.1 | Helped |
| use patch shuffle instead of Cutout (ablation) | SCO augmentation · iSAID | mIoU: 67.8 -> 69.1 | Helped |
| use patch shuffle instead of Mixup (ablation) | SCO augmentation · iSAID | mIoU: 68.1 -> 69.1 | Helped |
| use patch shuffle instead of Manifold Mixup (ablation) | SCO augmentation · iSAID | mIoU: 68.3 -> 69.1 | Helped |
| use patch shuffle instead of CutMix (ablation) | SCO augmentation · iSAID | mIoU: 68.5 -> 69.1 | Helped |
| increase patch shuffle augmentation count beyond 15 (ablation) | SCO · iSAID | mIoU | Hurt |
Closest papers by meaning
- Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation (AAAI 2025 · similarity 0.90)
- InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition (NeurIPS 2025 · similarity 0.88)
- In2NeCT: Inter-class and Intra-class Neural Collapse Tuning for Semantic Segmentation of Imbalanced Remote Sensing Images (AAAI 2025 · similarity 0.87)
- SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation (CVPR 2024 · similarity 0.87)
- SemStereo: Semantic-Constrained Stereo Matching Network for Remote Sensing (AAAI 2025 · similarity 0.87)
- LISAt: Language-Instructed Segmentation Assistant for Satellite Imagery (NeurIPS 2025 · similarity 0.87)
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.