Representation Learning with Deep Extreme Learning Machines for Efficient Image Set Classification
This addresses the problem of efficient and accurate image set classification for computer vision applications, offering a novel method that is incremental in improving existing approaches.
The paper tackles efficient image set classification by proposing a representation learning method using Deep Extreme Learning Machines (DELM) that avoids prior assumptions about data structure, achieving state-of-the-art performance in speed and accuracy across multiple public datasets.
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.