Suppressing label noise in medical image classification using mixup attention and self-supervised learning

Computer Science

• Classification Performance 33%
• Contrastive Learning 100%
• Deep Neural Network 100%
• Image Annotation 33%
• Image Classification 100%
• Performance Model 33%
• Self-Supervised Learning 100%
• Supervised Learning 33%
• Training Data 33%
• Visual Representation 33%

Keyphrases

• Label Noise 100%
• Learning Groups 25%
• Medical Image Annotation 25%
• Noisy Labels 50%
• Robust Training 25%