How to handle noisy labels for robust learning from uncertainty

This publication has 22 references indexed in Scilit:

• Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach
  2017
• Robust Web Image Annotation via Exploring Multi-Facet and Structural Knowledge
  IEEE Transactions on Image Processing, 2017
• Robust Semi-Supervised Classification for Noisy Labels Based on Self-Paced Learning
  IEEE Signal Processing Letters, 2016
• Identity Mappings in Deep Residual Networks
  2016
• Learning from Weak and Noisy Labels for Semantic Segmentation
  IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
• Classification with Noisy Labels by Importance Reweighting
  IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
• Joint Segmentation and Recognition of Categorized Objects From Noisy Web Image Collection
  IEEE Transactions on Image Processing, 2014
• Learning from multiple annotators with varying expertise
  Machine Learning, 2013
• Noise resistant graph ranking for improved web image search
  2011
• The general inefficiency of batch training for gradient descent learning
  Neural Networks, 2003