Skip to content
ModelListedExternal
Browse files

Galaxeye Eo Sar Change Detection

Lightweight multimodal EO--SAR change detection framework based on EfficientNet-B0 UNet architecture.

Sourcehuggingface.co/juggtimber/galaxeye-eo-sar-change-detection/tree/f4ba9cddf33b4dac6508a23d6b25493480f458ad
KindOtherBase modelgoogle/efficientnet-b0VersionRevision f4ba9cdCgrade

Model source

Kind
Other
File size
18.8–166 MB
Base model
google/efficientnet-b0
Version
vRevision f4ba9cd
Updated
Sep 16, 2026
Downloads
0
Source
Hugging Face

Source description

GalaxEye EO--SAR Change Detection

Lightweight multimodal EO--SAR change detection framework based on EfficientNet-B0 UNet architecture.

Overview

This model performs binary pixel-level change detection using paired Electro-Optical (EO) and Synthetic Aperture Radar (SAR) imagery.

The framework combines:

  • EO RGB channels
  • CLAHE-enhanced SAR
  • Log-transformed SAR

into a 5-channel multimodal segmentation input.

Architecture

  • EfficientNet-B0 encoder
  • UNet-style decoder
  • BCE + Dice + Focal hybrid loss

Results

SplitIoUF1
Validation0.27120.4267
Test0.08870.1629

Limitations

Performance degrades under cross-scene EO--SAR domain shift and heterogeneous SAR backscatter conditions.

Repository

GitHub repository: https://github.com/timbersaw-jugg/galaxeye-eo-sar-change-detection/

Sources

1 source
Hugging FacePrimaryVersion f4ba9cddf33b4dac6508a23d6b25493480f458ad
huggingface.co/juggtimber/galaxeye-eo-sar-change-detection/tree/f4ba9cddf33b4dac6508a23d6b25493480f458ad

Verified Sep 1

Download files

Model artifacts

2 artifacts

efficientnet_b0/best_model.pth

pth · 18.8 MB · SHA-256 5e9efee42c26…e968 · Hugging Face

Download file

resnet18/best_model.pth

pth · 166 MB · SHA-256 72d773480832…c1d1 · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeSep 1huggingface.co/juggtimber/galaxeye-eo-sar-change-detection

--- license: mit language: - en base_model: - google/efficientnet-b0 pipeline_tag: image-segmentation tags: - remote_sensing, - change_detection - eo - segmentation - efficientnet --- # GalaxEye EO--SAR Change Detection Lightweight multimodal EO--SAR change detection framework based on EfficientNet-B0 UNet architecture. ## Overview This model performs binary pixel-level change detection using paired Electro-Optical (EO) and Synthetic Aperture Radar (SAR) imagery. The framework combines: - EO RGB channels - CLAHE-enhanced SAR - Log-transformed SAR into a 5-channel multimodal segmentation input. ## Architecture - EfficientNet-B0 encoder - UNet-style decoder - BCE + Dice + Focal hybrid loss ## Results | Split | IoU | F1 | |---|---|---| | Validation | 0.2712 | 0.4267 | | Test | 0.0887 | 0.1629 | ## Limitations Performance degrades under cross-scene EO--SAR domain shift and heterogeneous SAR backscatter conditions. ## Repository GitHub repository: https://github.com/timbersaw-jugg/galaxeye-eo-sar-change-detection/

NoteSep 1huggingface.co/juggtimber/galaxeye-eo-sar-change-detection

Source context: 0 downloads · 0 likes · Pipeline image-segmentation · Repo juggtimber/galaxeye-eo-sar-change-detection