Research map / Detection and segmentation / Open-set and few-shot detection
SSL4EO-L: Datasets and Foundation Models for Landsat Imagery
Adam J Stewart, Nils Lehmann, Isaac Corley, Yi Wang, Yi-Chia Chang, Nassim Ait Ait Ali Braham, Shradha Sehgal, Caleb Robinson, Arindam Banerjee
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 |
|---|---|---|---|
| replace ImageNet pretraining with SSL4EO-L MoCo | ViT-S16 · L7 Irish cloud detection | accuracy: 68.22 -> 86.65 | Improved |
| replace ImageNet pretraining with SSL4EO-L MoCo | ViT-S16 · L7 Irish cloud detection | mIoU: 51.78 -> 76.03 | Improved |
| replace ImageNet pretraining with SSL4EO-L SimCLR | ViT-S16 · L7 Irish cloud detection | mIoU: 51.78 -> 70.47 | Improved |
| replace ImageNet pretraining with SSL4EO-L SimCLR | ResNet-18 · L7 Irish cloud detection | accuracy: 64.08 -> 34.80 | Hurt |
| replace ImageNet pretraining with SSL4EO-L MoCo | ResNet-18 · L8 Biome cloud detection | mIoU: 24.67 -> 27.33 | Improved |
| replace ImageNet pretraining with SSL4EO-L MoCo | ViT-S16 · L8 Biome cloud detection | mIoU: 30.98 -> 30.33 | Hurt |
| replace ImageNet pretraining with SSL4EO-L SimCLR | All backbones · Cloud detection (L7 Irish, L8 Biome) | accuracy/mIoU: 2 out of 6 | Mixed |
| replace ImageNet pretraining with SSL4EO-L MoCo | All backbones · NLCD and CDL land cover | accuracy/mIoU: 25 out of 30 | Improved |
| replace ImageNet pretraining with SSL4EO-L MoCo | ResNet-50 · NLCD, Landsat 4-5 TM TOA | mIoU: 49.96 -> 53.28 | Improved |
| replace ImageNet pretraining with SSL4EO-L MoCo | ResNet-50 · CDL, Landsat 7 ETM+ TOA | mIoU: 49.51 -> 47.19 | Hurt |
| replace ImageNet pretraining with SSL4EO-L SimCLR | All backbones · NLCD and CDL land cover | accuracy/mIoU: 24 out of 30 | Hurt |
| use SSL4EO-L MoCo gains on land cover (best case) | All backbones · NLCD and CDL land cover | accuracy/mIoU: 6.60% overall accuracy and 7.13 mIoU | Improved |
Closest papers by meaning
- Landsat30-AU: A Vision-Language Dataset for Australian Landsat Imagery (AAAI 2026 · similarity 0.88)
- SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing (AAAI 2024 · similarity 0.88)
- SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling (CVPR 2025 · similarity 0.87)
- CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models (NeurIPS 2025 · similarity 0.87)
- InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition (NeurIPS 2025 · similarity 0.87)
- GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution (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.
