Accurate and Efficient Similarity Search for Large Scale Face Recognition

TL;DR

This paper proposes a similarity search approach for large-scale face recognition that improves search speed and accuracy, achieving 3rd place with 1ms/image search time on a challenging dataset.

Contribution

It introduces a similarity search strategy for face recognition that enhances efficiency and accuracy without retraining the feature extraction model.

Findings

Achieved 3rd place in MS-Celeb-1M challenge 2.

Search speed of 1 millisecond per image.

Improved recognition performance through similarity search.

Abstract

Face verification is a relatively easy task with the help of discriminative features from deep neural networks. However, it is still a challenge to recognize faces on millions of identities while keeping high performance and efficiency. The challenge 2 of MS-Celeb-1M is a classification task. However, the number of identities is too large and it is not that elegant to treat the task as an image classification task. We treat the classification task as similarity search and do experiments on different similarity search strategies. Similarity search strategy accelerates the speed of searching and boosts the accuracy of final results. The model used for extracting features is a single deep neural network pretrained on CASIA-Webface, which is not trained on the base set or novel set offered by official. Finally, we rank \textbf{3rd}, while the speed of searching is 1ms/image.