Accelerated Training for Massive Classification via Dynamic Class Selection

01/05/2018
by   Xingcheng Zhang, et al.
0

Massive classification, a classification task defined over a vast number of classes (hundreds of thousands or even millions), has become an essential part of many real-world systems, such as face recognition. Existing methods, including the deep networks that achieved remarkable success in recent years, were mostly devised for problems with a moderate number of classes. They would meet with substantial difficulties, e.g. excessive memory demand and computational cost, when applied to massive problems. We present a new method to tackle this problem. This method can efficiently and accurately identify a small number of "active classes" for each mini-batch, based on a set of dynamic class hierarchies constructed on the fly. We also develop an adaptive allocation scheme thereon, which leads to a better tradeoff between performance and cost. On several large-scale benchmarks, our method significantly reduces the training cost and memory demand, while maintaining competitive performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/08/2018

Large-scale Bisample Learning on ID vs. Spot Face Recognition

In many face recognition applications, there is large amount of face dat...
research
05/24/2021

Dynamic Class Queue for Large Scale Face Recognition In the Wild

Learning discriminative representation using large-scale face datasets i...
research
05/05/2021

Prototype Memory for Large-scale Face Representation Learning

Face representation learning using datasets with massive number of ident...
research
05/22/2015

Efficient Large Scale Video Classification

Video classification has advanced tremendously over the recent years. A ...
research
07/18/2017

One-shot Face Recognition by Promoting Underrepresented Classes

We study in this paper the problem of one-shot face recognition, with th...
research
11/17/2016

PolyNet: A Pursuit of Structural Diversity in Very Deep Networks

A number of studies have shown that increasing the depth or width of con...

Please sign up or login with your details

Forgot password? Click here to reset