SpaceNet Comprehensive Astronomical Dataset

Description: SpaceNet Comprehensive Astronomical Dataset is a hierarchically structured and high-quality astronomical image dataset, created using a novel double-stage augmentation process. This dataset, comprising approximately 12,900 images, is designed for both fine-grained and macro classification tasks. SpaceNet incorporates a range of resolutions from lower (LR) to higher resolution (HR) images, using standard augmentations and a diffusion approach for generating synthetic samples. This allows for superior generalization across various recognition tasks such as classification. The dataset also includes diverse celestial objects, making it a valuable resource for both academic research and practical applications in astronomy and astrophysics. Download Dataset Dataset Structure: Fine-Grained Classes: The dataset includes 8 distinct classes: planets, galaxies, asteroids, nebulae, comets, black holes, stars, and constellations. Dataset Composition: Total Samples: Approximately 12,900 images Fine-Grained Class Distribution: Asteroid: 283 images Black Hole: 656 images Comet: 416 images Constellation: 1,552 images Galaxy: 3,984 images Nebula: 1,192 images Planet: 1,472 images Star: 3,269 images Usage: SpaceNet is ideal for: Training and evaluating machine learning models on fine-grained and macro astronomical classification tasks. Conducting research on hierarchical classification methods within the astronomy field. Developing robust models that demonstrate excellent generalization across both in-domain and out-of-domain datasets. This dataset is sourced from Kaggle.