Selective unsupervised feature learning with Convolutional Neural Network (S-CNN)

@article{Ghaderi2016SelectiveUF,
  title={Selective unsupervised feature learning with Convolutional Neural Network (S-CNN)},
  author={Amir Ghaderi and V. Athitsos},
  journal={2016 23rd International Conference on Pattern Recognition (ICPR)},
  year={2016},
  pages={2486-2490}
}
  • Amir Ghaderi, V. Athitsos
  • Published 2016
  • Computer Science
  • 2016 23rd International Conference on Pattern Recognition (ICPR)
  • Supervised learning of convolutional neural networks (CNNs) can require very large amounts of labeled data. Labeling thousands or millions of training examples can be extremely time consuming and costly. One direction towards addressing this problem is to create features from unlabeled data. In this paper we propose a new method for training a CNN, with no need for labeled instances. This method for unsupervised feature learning is then successfully applied to a challenging object recognition… CONTINUE READING
    A Review of Deep Learning Methods and Applications for Unmanned Aerial Vehicles
    • 105
    • PDF
    TUMK-ELM: A Fast Unsupervised Heterogeneous Data Learning Approach
    • 32
    • PDF
    Two-stage Unsupervised Multiple Kernel Extreme Learning Machine
    • 1

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 25 REFERENCES
    ImageNet classification with deep convolutional neural networks
    • 53,293
    • Highly Influential
    • PDF
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,628
    • PDF
    Learning Multiple Layers of Features from Tiny Images
    • 9,126
    • PDF
    ImageNet Large Scale Visual Recognition Challenge
    • 16,825
    • PDF
    Caffe: Convolutional Architecture for Fast Feature Embedding
    • 12,183
    • PDF
    Visualizing and Understanding Convolutional Networks
    • 8,439
    • PDF
    DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
    • 3,580
    • PDF
    Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
    • 3,544
    • PDF
    An Analysis of Single-Layer Networks in Unsupervised Feature Learning
    • 1,928
    • PDF