Log In Sign Up

Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning

by   Hailin Shi, et al.

With the recent development of deep convolutional neural networks and large-scale datasets, deep face recognition has made remarkable progress and been widely used in various applications. However, unlike the existing public face datasets, in many real-world scenarios of face recognition, the depth of training dataset is shallow, which means only two face images are available for each ID. With the non-uniform increase of samples, such issue is converted to a more general case, a.k.a long-tail face learning, which suffers from data imbalance and intra-class diversity dearth simultaneously. These adverse conditions damage the training and result in the decline of model performance. Based on the Semi-Siamese Training (SST), we introduce an advanced solution, named Multi-Agent Semi-Siamese Training (MASST), to address these problems. MASST includes a probe network and multiple gallery agents, the former aims to encode the probe features, and the latter constitutes a stack of networks that encode the prototypes (gallery features). For each training iteration, the gallery network, which is sequentially rotated from the stack, and the probe network form a pair of semi-siamese networks. We give theoretical and empirical analysis that, given the long-tail (or shallow) data and training loss, MASST smooths the loss landscape and satisfies the Lipschitz continuity with the help of multiple agents and the updating gallery queue. The proposed method is out of extra-dependency, thus can be easily integrated with the existing loss functions and network architectures. It is worth noting that, although multiple gallery agents are employed for training, only the probe network is needed for inference, without increasing the inference cost. Extensive experiments and comparisons demonstrate the advantages of MASST for long-tail and shallow face learning.


page 1

page 8


Semi-Siamese Training for Shallow Face Learning

Most existing public face datasets, such as MS-Celeb-1M and VGGFace2, pr...

Towards NIR-VIS Masked Face Recognition

Near-infrared to visible (NIR-VIS) face recognition is the most common c...

Open-set Face Recognition for Small Galleries Using Siamese Networks

Face recognition has been one of the most relevant and explored fields o...

End2End Occluded Face Recognition by Masking Corrupted Features

With the recent advancement of deep convolutional neural networks, signi...

Range Loss for Deep Face Recognition with Long-tail

Convolutional neural networks have achieved great improvement on face re...

Feature Transfer Learning for Deep Face Recognition with Long-Tail Data

Real-world face recognition datasets exhibit long-tail characteristics, ...

MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance

Deep Convolutional Neural Networks (DCNNs) and their variants have been ...