Representation Learning with Deep Extreme Learning Machines for Efficient Image Set Classification

TL;DR

This paper introduces a fast and effective method using Deep Extreme Learning Machines to represent image sets without prior assumptions, improving classification accuracy and speed on multiple datasets.

Contribution

It proposes a novel image set representation method with Deep Extreme Learning Machines that is efficient, assumption-free, and generalizes well with limited data.

Findings

Outperforms state-of-the-art methods in accuracy

Runs faster than existing approaches

Effective on diverse public datasets

Abstract

Efficient and accurate joint representation of a collection of images, that belong to the same class, is a major research challenge for practical image set classification. Existing methods either make prior assumptions about the data structure, or perform heavy computations to learn structure from the data itself. In this paper, we propose an efficient image set representation that does not make any prior assumptions about the structure of the underlying data. We learn the non-linear structure of image sets with Deep Extreme Learning Machines (DELM) that are very efficient and generalize well even on a limited number of training samples. Extensive experiments on a broad range of public datasets for image set classification (Honda/UCSD, CMU Mobo, YouTube Celebrities, Celebrity-1000, ETH-80) show that the proposed algorithm consistently outperforms state-of-the-art image set classification methods both in terms of speed and accuracy.