Deep supervised hashing for fast retrieval of radio image cubes

TL;DR

This paper introduces a deep supervised hashing method for rapid, scalable retrieval of similar radio image cubes, achieving high precision and efficiency in large astronomical datasets.

Contribution

It applies deep hashing techniques to radio astronomy image retrieval, demonstrating effective and scalable search capabilities in large-scale radio survey data.

Findings

Achieved 88.5% mean average precision in image retrieval

Demonstrated efficient search using Hamming distance in large datasets

Validated the method's scalability and effectiveness in radio astronomy

Abstract

The shear number of sources that will be detected by next-generation radio surveys will be astronomical, which will result in serendipitous discoveries. Data-dependent deep hashing algorithms have been shown to be efficient at image retrieval tasks in the fields of computer vision and multimedia. However, there are limited applications of these methodologies in the field of astronomy. In this work, we utilize deep hashing to rapidly search for similar images in a large database. The experiment uses a balanced dataset of 2708 samples consisting of four classes: Compact, FRI, FRII, and Bent. The performance of the method was evaluated using the mean average precision (mAP) metric where a precision of 88.5\% was achieved. The experimental results demonstrate the capability to search and retrieve similar radio images efficiently and at scale. The retrieval is based on the Hamming distance between the binary hash of the query image and those of the reference images in the database.