L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise

Yilun Xu, Peng Cao, Yuqing Kong, Yizhou Wang. L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alché-Buc, Edward A. Fox, Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada. pages 6222-6233, 2019. [doi]

@inproceedings{XuCKW19,
  title = {L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise},
  author = {Yilun Xu and Peng Cao and Yuqing Kong and Yizhou Wang},
  year = {2019},
  url = {http://papers.nips.cc/paper/8853-l_dmi-a-novel-information-theoretic-loss-function-for-training-deep-nets-robust-to-label-noise},
  researchr = {https://researchr.org/publication/XuCKW19},
  cites = {0},
  citedby = {0},
  pages = {6222-6233},
  booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada},
  editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alché-Buc and Edward A. Fox and Roman Garnett},
}