SupConViT – Supervised Contrastive Vision transformer for Supervised Contrastive Vision Transformer for Breast Histopathological Image Classification  

Description: A novel approach for improving the classification of invasive ductal carcinoma in terms accuracy and generalization by leveraging the inherent strengths and advantages of both transfer learning, i.e., pre-trained vision transformer and supervised contrastive learning. SupCon-Vit achieves state-of-the-art performance in IDC classification, with F1-score of 0.8188, precision of 0.7692, and specificity of 0.8971, outperforming existing methods.