The memorization problem is well-known in the field of computer vision. Liu et al. propose a technique called Early-Learning Regularization, which improves accuracy on the CIFAR datasets when label noise is present. This project replicates their experiments and investigates the performance on a real-world dataset with intrinsic noise. Results show that their experimental results are consistent. We also explore Sharpness-Aware Minimization in addition to SGD and observed a further 14.6 percentage points improvement. Future work includes using all 6 million images and manually clean a fraction of the images to fine-tune a transfer learning model. Last but not the least, having access to clean data for testing would also improve the measurement of accuracy.
@article{arxiv.2105.13244,
title = {Using Early-Learning Regularization to Classify Real-World Noisy Data},
author = {Alessio Galatolo and Alfred Nilsson and Roderick Karlemstrand and Yineng Wang},
journal= {arXiv preprint arXiv:2105.13244},
year = {2021}
}