FLARE up your data: Diffusion-based Augmentation Method in Astronomical Imaging

2024/05/22 by Mohammed Talha Alam, Raza Imam, Alam, Mohammed Talha +5 · 2 citations
Mathematics · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Statistical and numerical algorithms

paper · pdf · doi:10.48550/arxiv.2405.13267

openalex publication_date 2024/05/22 · openalex created_date 2024/05/25 · openalex updated_date 2026/07/28

Abstract

The intersection of Astronomy and AI encounters significant challenges related to issues such as noisy backgrounds, lower resolution (LR), and the intricate process of filtering and archiving images from advanced telescopes like the James Webb. Given the dispersion of raw images in feature space, we have proposed a two-stage augmentation framework entitled as FLARE based on \underlinefeature \underlinelearning and \underlineaugmented \underlineresolution \underlineenhancement. We first apply lower (LR) to higher resolution (HR) conversion followed by standard augmentations. Secondly, we integrate a diffusion approach to synthetically generate samples using class-concatenated prompts. By merging these two stages using weighted percentiles, we realign the feature space distribution, enabling a classification model to establish a distinct decision boundary and achieve superior generalization on various in-domain and out-of-domain tasks. We conducted experiments on several downstream cosmos datasets and on our optimally distributed SpaceNet dataset across 8-class fine-grained and 4-class macro classification tasks. FLARE attains the highest performance gain of 20.78% for fine-grained tasks compared to similar baselines, while across different classification models, FLARE shows a consistent increment of an average of +15%. This outcome underscores the effectiveness of the FLARE method in enhancing the precision of image classification, ultimately bolstering the reliability of astronomical research outcomes. % Our code and SpaceNet dataset will be released to the public soon. Our code and SpaceNet dataset is available at \hrefhttps://github.com/Razaimam45/PlanetX_Dxbhttps://github.com/Razaimam45/PlanetX_Dxb.

Cited by

• AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection
• ADAM-Dehaze: Adaptive Density-Aware Multi-Stage Dehazing for Improved Object Detection in Foggy Conditions

Related

• BGRem: A background noise remover for astronomical images based on a diffusion model
• AstroSpy: On detecting Fake Images in Astronomy via Joint Image-Spectral Representations
• Applications of AI in Astronomy
• DiffLense: A Conditional Diffusion Model for Super-Resolution of Gravitational Lensing Data
• AstroPT: Scaling Large Observation Models for Astronomy