Learning From Noisy Labels With Deep Neural Networks: A Survey

🤖 Plain-English Summary

Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. Subsequently, we perform an in-depth analysis of noise rate estimation and summarize the typically used evaluation methodology, including public noisy datasets and evaluation metrics.

🔑 Key Findings

• However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios.
• As noisy labels severely degrade the generalization performance of deep neural networks, learning from noisy labels (robust training) is becoming an important task in modern deep learning applications.
• In this survey, we first describe the problem of learning with label noise from a supervised learning perspective.

🔗 Related Resources