Search results
Jump to navigation
Jump to search
Page title matches
Page text matches
- 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) - 20:02, 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) - 19:40, 28 November 2017