Topological RANSAC for instance verification and retrieval without fine-tuning

TL;DR

This paper introduces a topological RANSAC method that improves instance verification and retrieval without fine-tuning, outperforming traditional spatial verification by leveraging topological relations and bio-inspired functions.

Contribution

We replace the spatial model in RANSAC with a topological approach using bio-inspired functions, enabling explainable, lightweight, and high-performance image retrieval without fine-tuning.

Findings

Outperforms spatial verification in non-fine-tuning retrieval tasks

Enhances performance when combined with fine-tuned features

Maintains high explainability and lightweight design

Abstract

This paper presents an innovative approach to enhancing explainable image retrieval, particularly in situations where a fine-tuning set is unavailable. The widely-used SPatial verification (SP) method, despite its efficacy, relies on a spatial model and the hypothesis-testing strategy for instance recognition, leading to inherent limitations, including the assumption of planar structures and neglect of topological relations among features. To address these shortcomings, we introduce a pioneering technique that replaces the spatial model with a topological one within the RANSAC process. We propose bio-inspired saccade and fovea functions to verify the topological consistency among features, effectively circumventing the issues associated with SP's spatial model. Our experimental results demonstrate that our method significantly outperforms SP, achieving state-of-the-art performance in non-fine-tuning retrieval. Furthermore, our approach can enhance performance when used in conjunction with fine-tuned features. Importantly, our method retains high explainability and is lightweight, offering a practical and adaptable solution for a variety of real-world applications.