Challenging deep image descriptors for retrieval in heterogeneous iconographic collections

TL;DR

This paper evaluates the robustness of recent deep-learning image descriptors in content-based retrieval tasks across diverse and complex cultural image collections with multiple sources, dates, and views.

Contribution

It provides a comprehensive analysis of how current deep image descriptors perform on heterogeneous cultural datasets, highlighting their strengths and limitations.

Findings

Deep descriptors show varying robustness across different cultural datasets.

Certain descriptors outperform others in multi-source and multi-view scenarios.

The study identifies key challenges for improving deep image retrieval in heterogeneous collections.

Abstract

This article proposes to study the behavior of recent and efficient state-of-the-art deep-learning based image descriptors for content-based image retrieval, facing a panel of complex variations appearing in heterogeneous image datasets, in particular in cultural collections that may involve multi-source, multi-date and multi-view Permission to make digital