Deep one-class probability learning for end-to-end image classification.

Journal: Neural networks : the official journal of the International Neural Network Society
PMID:

Abstract

One-class learning has many application potentials in novelty, anomaly, and outlier detection systems. It aims to distinguish both positive and negative samples with a model trained via only positive samples or one-class annotated samples. With the difficulty in training an end-to-end classification network, existing methods usually make decisions indirectly. To fully exploit the learning capability of a deep network, in this paper, we propose to design a deep end-to-end binary image classifier based on convolutional neural network with input of image and output of classification result. Without negative training samples, we establish a probabilistic model driven by an energy to learn the distribution of positive samples. The energy is proposed based on the output of the network which subtly models the deep discriminations into statistics. During optimization, to overcome the difficulty of distribution estimation, we propose a novel particle swarm optimization algorithm based sampling method. Compared with existing methods, the proposed method is able to directly output classification results without additional thresholding or estimating operations. Moreover, the deep network is directly optimized via the probabilistic model which results in better adaptation of positive distribution and classification task. Experiments demonstrate the effectiveness and state-of-the-art performance of the proposed method.

Authors

  • Jia Liu
    Department of Colorectal Oncology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Tianjin Key Laboratory of Digestive Cancer, Tianjin, China.
  • Wenhua Zhang
    Department of Cancer Epidemiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China.
  • Fang Liu
    The First Clinical Medical College of Gannan Medical University, Ganzhou 341000, Jiangxi Province, China.
  • Jingxiang Yang
    School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China.
  • Liang Xiao