This assignment is designed to tackle the problem of image classification in the presence of noisy labels, a common issue in real-world datasets where the labels may be incorrectly assigned due to human error, automated labeling processes, or inherent ambiguities in the data. 

The objective of this assignment is to perform image classification on the CIFAR-100 dataset, where 40% of the labels have been deliberately corrupted randomly. The goal is to evaluate the robustness and performance of the Vision Transformer (ViT) model in the presence of noisy labels.