Fast Training of Deep Networks with One-Class CNNs

EasyChair Preprint 3930

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.

Keyphrases: Caltech 101, One-Class CNNs, Rapid Convergence, deep learning, fast training

@booklet{EasyChair:3930,
  author    = {Abdul Mueed Hafiz and Ghulam Mohiuddin Bhat},
  title     = {Fast Training of Deep Networks with One-Class CNNs},
  howpublished = {EasyChair Preprint 3930},
  year      = {EasyChair, 2020}}