Enhancing Noisy Label Learning Via Unsupervised Contrastive Loss with Label Correction Based on Prior Knowledge.
Masaki KashiwagiKeisuke MaedaRen TogoTakahiro OgawaMiki HaseyamaPublished in: ICASSP (2024)
Keyphrases
- prior knowledge
- supervised learning
- learning process
- learning systems
- learning algorithm
- bayesian framework
- multi label
- class labels
- decision trees
- reinforcement learning
- markov random field
- unsupervised learning
- semi supervised
- hidden markov models
- learning tasks
- learning problems
- bayesian networks
- learning scenarios
- learning community
- unsupervised manner
- multi label learning
- preference learning
- label ranking
- label noise