SpaceNet: A Comprehensive Astronomical Dataset

Key Features

• High-Resolution Images: The dataset includes high-quality images that facilitate accurate analysis and classification.
• Hierarchical Structure: The dataset is hierarchically organized to support both macro and fine-grained classification tasks.
• Advanced Augmentation Techniques: Utilizes FLARE framework for double-stage augmentation, enhancing the dataset’s diversity and robustness.
• Synthetic Sample Generation: Employs a diffusion approach to create synthetic samples, boosting the dataset’s size and variability.
  

  Usage

  SpaceNet is ideal for:

  • Training and Evaluation: Developing and testing machine learning models for fine-grained and macro astronomical classification tasks.
  • Research: Exploring hierarchical classification approaches within the astronomy domain.
  • Model Development: Creating robust models capable of generalizing across both in-domain and out-of-domain datasets.
  • Educational Purposes: Providing a rich dataset for educational projects in astronomy and machine learning.