Learning from Noisy Labeled Data Using Symmetric Cross-Entropy Loss for Image Classification.
Hiroshi TakedaSoh YoshidaMitsuji MuneyasuPublished in: GCCE (2020)
Keyphrases
- labeled data
- supervised learning
- image classification
- cross entropy
- unlabeled data
- active learning
- learning algorithm
- domain adaptation
- semi supervised
- prior knowledge
- semi supervised learning
- labeled and unlabeled data
- learning process
- training data
- unsupervised learning
- transfer learning
- text classification
- co training
- dimensionality reduction
- neural network
- data points
- information retrieval
- class labels
- learning tasks
- machine learning