Using Early-Learning Regularization to Classify Real-World Noisy Data
Reviewed by Pithpith:3E5UYKBLopen to challenge →
read the original abstract
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.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.