FASON: First and Second Order Information Fusion Network for Texture Recognition

@article{Dai2017FASONFA,
  title={FASON: First and Second Order Information Fusion Network for Texture Recognition},
  author={Xiyang Dai and Joe Yue-Hei Ng and Larry S. Davis},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={6100-6108}
}
Deep networks have shown impressive performance on many computer vision tasks. Recently, deep convolutional neural networks (CNNs) have been used to learn discriminative texture representations. One of the most successful approaches is Bilinear CNN model that explicitly captures the second order statistics within deep features. However, these networks cut off the first order information flow in the deep network and make gradient back-propagation difficult. We propose an effective fusion… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 34 references

Similar Papers

Loading similar papers…