Range Loss for Deep Face Recognition with Long-Tailed Training Data

Abstract

Convolutional neural networks have achieved great improvement on face recognition in recent years because of its extraordinary ability in learning discriminative features of people with different identities. To train such a welldesigned deep network, tremendous amounts of data is indispensable. Long tail distribution specifically refers to the fact that a small number of generic entities appear frequently while other objects far less existing. Considering the existence of long tail distribution of the real world data, large but uniform distributed data are usually hard to retrieve. Empirical experiences and analysis show that classes with more samples will pose greater impact on the feature learning process [37,19] and inversely cripple the whole models feature extracting ability on tail part data. Contrary to most of the existing works that alleviate this problem by simply cutting the tailed data for uniform distributions across the classes, this paper proposes a new loss function called range loss to effectively utilize the whole long tailed data in training process. More specifically, range loss is designed to reduce overall intrapersonal variations while enlarging inter-personal differences within one mini-batch simultaneously when facing even extremely unbalanced data. The optimization objective of range loss is the k greatest range's harmonic mean values in one class and the shortest inter-class distance within one batch. Extensive experiments on two famous and challenging face recognition benchmarks (Labeled Faces in the Wild (LFW) [12] and YouTube Faces (YTF) [31]) not only demonstrate the effectiveness of the proposed approach in overcoming the long tail effect but also show the good generalization ability of the proposed approach.

Large-Scale Bisample Learning on ID Versus Spot Face Recognition

“…[45] makes samples uniformly distributed by random sampling. [31] proposes a range loss to balance the rich and poor classes, where the largest intra-class distance is reduced and the shortest class-center distance is enlarged.…”

P2SGrad: Refined Gradients for Optimizing Deep Face Models

“…In the early years, most face recognition approaches utilized metric loss functions, such as triplet loss [30] and contrastive loss [2], which use Euclidean margin to measure distance between features. Taking advantages of these works, center loss [31] and range loss [33] were proposed to reduce intra-class variations through minimizing distance within target classes [1].…”

Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition

“…One category is loss functions that optimize the Euclidean distance. Examples include contrastive loss [23], range loss [31], triplet loss [22], center loss [27] and marginal loss [8]. They cluster samples from the same identity by minimizing the intra-class Euclidean distances.…”

“…It is robust to unbalanced distribution over identities (e.g. long-tailed distribution [31]). Even many of the identities have only one or two images in the unlabeled dataset, our proposed UIR loss is still able to utilize them without attenuating the performance.…”