Research map / Detection and segmentation / Open-set and few-shot detection
LaVIDE: Language-Prompted Satellite Change Detection via Map-Image Alignment
Shuguo Jiang, Fang Xu, Chuandong Liu, Hong Tan, Shengyang Li, Lei Yu, Wen Tao Yang, Sen Jia, Gui-Song Xia
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 |
|---|---|---|---|
| encode the map with language prompts instead of color (ablation) | LaVIDE · DynamicEarthNet | IoU: 20.3 -> 23.2 | Improved |
| encode the map with language prompts instead of numbers (ablation) | LaVIDE · DynamicEarthNet | IoU: 20.2 -> 23.2 | Improved |
| encode the map with language prompts instead of one-hot (ablation) | LaVIDE · DynamicEarthNet | IoU: 20.0 -> 23.2 | Improved |
| encode the map with language instead of color/number/one-hot (ablation) | LaVIDE · BANDON | IoU: 56.3 -> 57.5 | Improved |
| add the phrase 'in the scene' to brief handcrafted prompt (ablation) | A photo of the C prompt · DynamicEarthNet | IoU: 18.3 -> 21.9 | Improved |
| use detailed attribute prompt instead of plain brief prompt (ablation) | prompt design · DynamicEarthNet | IoU: 18.3 -> 19.3 | Improved |
| make prompt tokens learnable (ablation) | A photo of the C prompt · DynamicEarthNet | IoU: 18.3 -> 21.3 | Improved |
| add 'in the scene' constraint to learnable prompts (restricted prompt learning) (ablation) | learnable prompts · DynamicEarthNet | IoU: 21.3 -> 23.2 | Improved |
| add object-aware embedding enhancement (OAEE) (ablation) | baseline · DynamicEarthNet | IoU: 20.4 -> 21.5 | Improved |
| add knowledge distillation (KD) from the language-vision encoder (ablation) | baseline · DynamicEarthNet | IoU: 20.4 -> 22.0 | Improved |
| add KD on top of OAEE (ablation) | LaVIDE with OAEE · DynamicEarthNet | IoU: 21.5 -> 23.2 | Improved |
| add OAEE on top of KD (ablation) | LaVIDE with KD · DynamicEarthNet | IoU: 22.0 -> 23.2 | Improved |
Closest papers by meaning
- RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-𝑁 Ranking (NeurIPS 2026 · similarity 0.89)
- The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generationf (CVPR 2025 · similarity 0.88)
- UniChange: Unifying Change Detection with Multimodal Large Language Model (CVPR 2026 · similarity 0.88)
- TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data (ICLR 2025 · similarity 0.88)
- SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling (CVPR 2025 · similarity 0.88)
- Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community (AAAI 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.
