Quantum Visual Feature Encoding Revisited

TL;DR

This paper identifies a fundamental information loss issue in quantum visual encoding for machine learning, introduces a new loss function to preserve information, and demonstrates improved performance and state-of-the-art results.

Contribution

It uncovers the Quantum Information Gap problem in quantum visual encoding and proposes a novel loss function to address it, enhancing quantum machine learning performance.

Findings

QIG causes significant information loss in quantum encoding.

QIP loss function effectively minimizes QIG.

Achieves state-of-the-art results in quantum vision tasks.

Abstract

Although quantum machine learning has been introduced for a while, its applications in computer vision are still limited. This paper, therefore, revisits the quantum visual encoding strategies, the initial step in quantum machine learning. Investigating the root cause, we uncover that the existing quantum encoding design fails to ensure information preservation of the visual features after the encoding process, thus complicating the learning process of the quantum machine learning models. In particular, the problem, termed "Quantum Information Gap" (QIG), leads to a gap of information between classical and corresponding quantum features. We provide theoretical proof and practical demonstrations of that found and underscore the significance of QIG, as it directly impacts the performance of quantum machine learning algorithms. To tackle this challenge, we introduce a simple but efficient new loss function named Quantum Information Preserving (QIP) to minimize this gap, resulting in enhanced performance of quantum machine learning algorithms. Extensive experiments validate the effectiveness of our approach, showcasing superior performance compared to current methodologies and consistently achieving state-of-the-art results in quantum modeling.