Search results

Jump to navigation Jump to search
  • Co-teaching: Robust Training Deep Neural Networks with Extremely Noisy Labels ...5% of noisy labels), the robustness of deep learning models trained by the co-teaching approach is much superior to state-of-the-art baselines ...
    15 KB (2,318 words) - 21:02, 11 December 2018
  • [[File:7.png|center|600px]] ...p, more units dropped). The relevant numerical results have been shown in table 1-5. ...
    20 KB (3,272 words) - 20:40, 28 November 2017