Research map / Time series / Foundation models for time series
DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change 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 |
|---|---|---|---|
| Add unlabeled daily images to semi-supervised training instead of using labeled monthly images only | CAC with DeepLabv3+ · DynamicEarthNet test | mIoU: 37.9 -> 43.6 | Helped |
| Add unlabeled weekly images to semi-supervised training instead of using labeled monthly images only | CAC with DeepLabv3+ · DynamicEarthNet test | mIoU: 37.9 -> 37.9 | No clear effect |
| Use weekly rather than monthly temporal inputs | Spatio-temporal baselines · DynamicEarthNet validation | mIoU: 33.5 -> 35.7 | Helped |
| Use daily rather than weekly temporal inputs | Spatio-temporal baselines · DynamicEarthNet test | mIoU: 39.7 -> 36.1; 39.1 -> 30.9 | Hurt |
| Use daily rather than weekly samples | CAC semi-supervised baseline · DynamicEarthNet test | SCS: 17.8 -> 18.5 | Helped |
| Use daily rather than weekly temporal inputs | Spatio-temporal baselines · DynamicEarthNet test | SCS: 19.1 -> 17.8; 19.0 -> 15.6; 17.6 -> 18.8 | Mixed |
| Evaluate change across all viable month pairs rather than only consecutive months | Weekly baselines · DynamicEarthNet test | SCS: 19.1 -> 27.6; 19.0 -> 27.5; 17.6 -> 25.3; 17.8 -> 27.7 | Helped |
| Focus semantic scoring on ground-truth changed pixels and report binary change separately | Semantic change evaluation protocol · DynamicEarthNet semantic change segmentation | SCS | Helped |
Closest papers by meaning
- The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generationf (CVPR 2025 · similarity 0.88)
- DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding (NeurIPS 2025 · similarity 0.86)
- Exact: Exploring Space-Time Perceptive Clues for Weakly Supervised Satellite Image Time Series Semantic Segmentation (CVPR 2025 · similarity 0.86)
- RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-𝑁 Ranking (NeurIPS 2026 · similarity 0.86)
- TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data (ICLR 2025 · similarity 0.86)
- FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding (NeurIPS 2024 · similarity 0.86)
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.