Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification

@article{Bae2017BeyondDR,
  title={Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification},
  author={Woong Jin Bae and Jae Jun Yoo and Jong Chul Ye},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2017},
  pages={1141-1149}
}
The latest deep learning approaches perform better than the state-of-the-art signal processing approaches in various image restoration tasks. However, if an image contains many patterns and structures, the performance of these CNNs is still inferior. To address this issue, here we propose a novel feature space deep residual learning algorithm that outperforms the existing residual learning. The main idea is originated from the observation that the performance of a learning algorithm can be… CONTINUE READING
Tweets
This paper has been referenced on Twitter 41 times. VIEW TWEETS

Citations

Publications citing this paper.
SHOWING 1-10 OF 25 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 32 REFERENCES

Similar Papers

Loading similar papers…