Local Orthogonal-Group Testing

TL;DR

This paper introduces a local orthogonal-group testing method for large-scale image retrieval that improves search efficiency and accuracy by using orthogonal grouping and local processing, suitable for batch and parallel data handling.

Contribution

It proposes a novel local orthogonal-group testing approach with efficient off-line structure construction, enhancing approximate nearest neighbor search in large-scale image retrieval.

Findings

Achieves search accuracy comparable to exhaustive search.

Significantly reduces search complexity.

Compatible with existing embedding methods.

Abstract

This work addresses approximate nearest neighbor search applied in the domain of large-scale image retrieval. Within the group testing framework we propose an efficient off-line construction of the search structures. The linear-time complexity orthogonal grouping increases the probability that at most one element from each group is matching to a given query. Non-maxima suppression with each group efficiently reduces the number of false positive results at no extra cost. Unlike in other well-performing approaches, all processing is local, fast, and suitable to process data in batches and in parallel. We experimentally show that the proposed method achieves search accuracy of the exhaustive search with significant reduction in the search complexity. The method can be naturally combined with existing embedding methods.