Similarity Guided Deep Face Image Retrieval

TL;DR

This paper introduces a Similarity Guided Hashing (SGH) method that enhances deep face image retrieval by considering both self and pairwise similarities, leading to state-of-the-art results on multiple benchmarks.

Contribution

The paper proposes a novel SGH approach that incorporates similarity guidance and data augmentation to improve face image retrieval beyond classification-based hashing methods.

Findings

SGH achieves superior retrieval accuracy on benchmark datasets.

Data augmentation helps explore complex face image similarities.

SGH outperforms existing deep face hashing methods.

Abstract

Face image retrieval, which searches for images of the same identity from the query input face image, is drawing more attention as the size of the image database increases rapidly. In order to conduct fast and accurate retrieval, a compact hash code-based methods have been proposed, and recently, deep face image hashing methods with supervised classification training have shown outstanding performance. However, classification-based scheme has a disadvantage in that it cannot reveal complex similarities between face images into the hash code learning. In this paper, we attempt to improve the face image retrieval quality by proposing a Similarity Guided Hashing (SGH) method, which gently considers self and pairwise-similarity simultaneously. SGH employs various data augmentations designed to explore elaborate similarities between face images, solving both intra and inter identity-wise difficulties. Extensive experimental results on the protocols with existing benchmarks and an additionally proposed large scale higher resolution face image dataset demonstrate that our SGH delivers state-of-the-art retrieval performance.