BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition

by   Yonghyun Kim, et al.

The datasets of face recognition contain an enormous number of identities and instances. However, conventional methods have difficulty in reflecting the entire distribution of the datasets because a mini-batch of small size contains only a small portion of all identities. To overcome this difficulty, we propose a novel method called BroadFace, which is a learning process to consider a massive set of identities, comprehensively. In BroadFace, a linear classifier learns optimal decision boundaries among identities from a large number of embedding vectors accumulated over past iterations. By referring more instances at once, the optimality of the classifier is naturally increased on the entire datasets. Thus, the encoder is also globally optimized by referring the weight matrix of the classifier. Moreover, we propose a novel compensation method to increase the number of referenced instances in the training stage. BroadFace can be easily applied on many existing methods to accelerate a learning process and obtain a significant improvement in accuracy without extra computational burden at inference stage. We perform extensive ablation studies and experiments on various datasets to show the effectiveness of BroadFace, and also empirically prove the validity of our compensation method. BroadFace achieves the state-of-the-art results with significant improvements on nine datasets in 1:1 face verification and 1:N face identification tasks, and is also effective in image retrieval.


page 1

page 2

page 3

page 4


GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition

In the field of face recognition, a model learns to distinguish millions...

Dataset Cleaning – A Cross Validation Methodology for Large Facial Datasets using Face Recognition

In recent years, large "in the wild" face datasets have been released in...

Identifying Avatar Aliases in Starcraft 2

In electronic sports, cyberathletes conceal their online training using ...

An Efficient Training Approach for Very Large Scale Face Recognition

Face recognition has achieved significant progress in deep-learning era ...

Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association

Nowadays, we have witnessed the early progress on learning the associati...

How to Train Triplet Networks with 100K Identities?

Training triplet networks with large-scale data is challenging in face r...

Information Maximization for Extreme Pose Face Recognition

In this paper, we seek to draw connections between the frontal and profi...

Please sign up or login with your details

Forgot password? Click here to reset