Dynamic Class Queue for Large Scale Face Recognition In the Wild

by   Bi Li, et al.

Learning discriminative representation using large-scale face datasets in the wild is crucial for real-world applications, yet it remains challenging. The difficulties lie in many aspects and this work focus on computing resource constraint and long-tailed class distribution. Recently, classification-based representation learning with deep neural networks and well-designed losses have demonstrated good recognition performance. However, the computing and memory cost linearly scales up to the number of identities (classes) in the training set, and the learning process suffers from unbalanced classes. In this work, we propose a dynamic class queue (DCQ) to tackle these two problems. Specifically, for each iteration during training, a subset of classes for recognition are dynamically selected and their class weights are dynamically generated on-the-fly which are stored in a queue. Since only a subset of classes is selected for each iteration, the computing requirement is reduced. By using a single server without model parallel, we empirically verify in large-scale datasets that 10 using all classes. Moreover, the class weights are dynamically generated in a few-shot manner and therefore suitable for tail classes with only a few instances. We show clear improvement over a strong baseline in the largest public dataset Megaface Challenge2 (MF2) which has 672K identities and over 88 of them have less than 10 instances. Code is available at https://github.com/bilylee/DCQ


page 1

page 2

page 3

page 4


Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC

Learning discriminative deep feature embeddings by using million-scale i...

Lesion-Aware Contrastive Representation Learning for Histopathology Whole Slide Images Analysis

Local representation learning has been a key challenge to promote the pe...

Accelerated Training for Massive Classification via Dynamic Class Selection

Massive classification, a classification task defined over a vast number...

Large-Scale Long-Tailed Recognition in an Open World

Real world data often have a long-tailed and open-ended distribution. A ...

Improving Calibration for Long-Tailed Recognition

Deep neural networks may perform poorly when training datasets are heavi...

Range Loss for Deep Face Recognition with Long-tail

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

Sparse Representation-based Open Set Recognition

We propose a generalized Sparse Representation- based Classification (SR...

Please sign up or login with your details

Forgot password? Click here to reset