Fast Training of Deep Networks with One-Class CNNs

TL;DR

This paper introduces a multiclass classification method using one-class CNNs trained per class, achieving better accuracy and faster training times compared to traditional multi-class networks, demonstrated on face and object recognition tasks.

Contribution

It extends one-class CNNs to multiclass classification by training separate CNNs per class and combining them, which is a novel approach in this domain.

Findings

Achieves higher recognition accuracy

Reduces training time by half or two-thirds

Successfully applied to face and object recognition

Abstract

One-class CNNs have shown promise in novelty detection. However, very less work has been done on extending them to multiclass classification. The proposed approach is a viable effort in this direction. It uses one-class CNNs i.e., it trains one CNN per class, for multiclass classification. An ensemble of such one-class CNNs is used for multiclass classification. The benefits of the approach are generally better recognition accuracy while taking almost even half or two-thirds of the training time of a conventional multi-class deep network. The proposed approach has been applied successfully to face recognition and object recognition tasks. For face recognition, a 1000 frame RGB video, featuring many faces together, has been used for benchmarking of the proposed approach. Its database is available on request via e-mail. For object recognition, the Caltech-101 Image Database and 17Flowers Dataset have also been used. The experimental results support the claims made.