Hybrid U-Net augmented with Clay GFM context via two-stage LoRA reaches 64.5% test F1 on Landslide4Sense, beating both standalone Clay (55.2%) and plain U-Net (59.9%).
A feature fusion method on landslide identification in remote sensing with Segment Anything Model,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LandslideAgent is a rule-augmented agent built on a fine-tuned landslide VLM and a new multimodal benchmark dataset that reports accuracy gains in classification, segmentation, and description tasks.
citing papers explorer
-
Clay-CNN Hybrids: Leveraging Geospatial Foundation Models as Auxiliary Context for Landslide Detection
Hybrid U-Net augmented with Clay GFM context via two-stage LoRA reaches 64.5% test F1 on Landslide4Sense, beating both standalone Clay (55.2%) and plain U-Net (59.9%).
-
LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis
LandslideAgent is a rule-augmented agent built on a fine-tuned landslide VLM and a new multimodal benchmark dataset that reports accuracy gains in classification, segmentation, and description tasks.