Scale Aware Recognition in Satellite Images under Resource Constraints

Published as a conference paper at ICLR 2025

Authors: Shreelekha Revankar¹*, Cheng Perng Phoo¹, Utkarsh Mall², Bharath Hariharan¹, Kavita Bala¹

¹Cornell University ²Columbia University

This repository contains the official implementation of our ICLR 2025 paper: Scale-Aware Recognition in Satellite Images Under Resource Constraints.

Getting Started

Setting up the Python Environment

# Clone the repository
git clone https://github.com/ShreelekhaR/scale-aware.git
cd scale-aware

# Create the conda environment from the provided environment.yml file
conda env create -f environment.yml

# OR create your own python environment
conda create -n scale_aware python=3.10

# Install PyTorch (adjust according to your CUDA version if applicable)
pip install torch torchvision

# Install the required packages
pip install -r requirements.txt

Demo

coming soon

Dataset & Training

To download our data and train the models, please refer to our Training and Data Guide.

Inference

Citation

If you find our work useful in your research, please consider citing:

@article{revankar2024scale,
    title={Scale-Aware Recognition in Satellite Images under Resource Constraint},
    author={Revankar, Shreelekha and Phoo, Cheng Perng and Mall, Utkarsh and Hariharan, Bharath and Bala, Kavita},
    journal={ICLR},
    year={2025}
}