论文标题
用一级CNN快速培训深层网络
Fast Training of Deep Networks with One-Class CNNs
论文作者
论文摘要
一级CNN在新颖性检测中表现出了希望。但是，将它们扩展到多类分类的工作要少。提出的方法是在这个方向上的可行努力。它使用一级CNN，即，它每类训练一个CNN进行多类分类。这种单级CNN的合奏用于多类分类。该方法的好处通常是更好的识别精度，同时将几乎一半或三分之二的训练时间占常规多级深网的训练时间。提出的方法已成功地应用于面对识别和对象识别任务。为了进行面部识别，已使用1000帧的RGB视频一起进行了许多面孔，用于对拟议方法进行基准测试。可以根据电子邮件获得其数据库。为了识别对象识别，也使用了CalTech-101图像数据库和17Flower数据集。实验结果支持提出的主张。
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.
