Benchmarking Deep Learning-Based Object Detection Models on Feature Deficient Astrophotography Imagery Dataset

2025/08/04 by Shantanusinh Parmar, Parmar, Shantanusinh · 1 citation
Computer Science · Engineering · Environmental Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Physical sciences #Impact of Light on Environment and Health #Infrared Target Detection Methodologies #Instrumentation and Methods for Astrophysics (astro-ph.IM)

paper · pdf · doi:10.48550/arxiv.2508.06537

openalex publication_date 2025/08/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Object detection models are typically trained on datasets like ImageNet, COCO, and PASCAL VOC, which focus on everyday objects. However, these lack signal sparsity found in non-commercial domains. MobilTelesco, a smartphone-based astrophotography dataset, addresses this by providing sparse night-sky images. We benchmark several detection models on it, highlighting challenges under feature-deficient conditions.

Citations

• YOLOv12: Attention-Centric Real-Time Object Detectors
• PP-YOLOE: An evolved version of YOLO
• Multiple instance active learning for object detection
• Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
• Towards Noise-resistant Object Detection with Noisy Annotations
• Training Object Detectors With Noisy Data
• The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Deep Residual Learning for Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Microsoft COCO: Common Objects in Context
• ASTROMETRY.NET: BLIND ASTROMETRIC CALIBRATION OF ARBITRARY ASTRONOMICAL IMAGES

Cited by

• StrCGAN: A Generative Framework for Stellar Image Restoration

Related

• Evaluation and Analysis of Deep Neural Transformers and Convolutional Neural Networks on Modern Remote Sensing Datasets
• Robustness analysis of Deep Sky Objects detection models on HPC
• FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery
• Detecting Moving Objects With Machine Learning
• Resource-Constrained Simultaneous Detection and Labeling of Objects in High-Resolution Satellite Images