Accurate and Efficient Similarity Search for Large Scale Face Recognition
This addresses the problem of efficient large-scale face recognition for applications like security or social media, but it is incremental as it applies existing similarity search strategies to a known bottleneck.
The paper tackled the challenge of performing face recognition on millions of identities by treating it as a similarity search problem, achieving a 3rd-place ranking with a search speed of 1ms per image.
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.