Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels
Ganlong Zhao, Guanbin Li, Yipeng Qin, Feng Liu, Yizhou Yu
Topics & Concepts
Computer scienceArtificial intelligenceClassifier (UML)Ground truthConsistency (knowledge bases)Class (philosophy)Machine learningNoise (video)Identification (biology)Entropy (arrow of time)Pattern recognition (psychology)Data miningBotanyImage (mathematics)BiologyQuantum mechanicsPhysicsMachine Learning and Data ClassificationAnomaly Detection Techniques and ApplicationsAdvanced Neural Network Applications