تقرير
Deep Learning with Label Noise: A Hierarchical Approach
| العنوان: | Deep Learning with Label Noise: A Hierarchical Approach |
|---|---|
| المؤلفون: | Chen, Li, Huang, Ningyuan, Mu, Cong, Helm, Hayden S., Lytvynets, Kate, Yang, Weiwei, Priebe, Carey E. |
| سنة النشر: | 2022 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | Deep neural networks are susceptible to label noise. Existing methods to improve robustness, such as meta-learning and regularization, usually require significant change to the network architecture or careful tuning of the optimization procedure. In this work, we propose a simple hierarchical approach that incorporates a label hierarchy when training the deep learning models. Our approach requires no change of the network architecture or the optimization procedure. We investigate our hierarchical network through a wide range of simulated and real datasets and various label noise types. Our hierarchical approach improves upon regular deep neural networks in learning with label noise. Combining our hierarchical approach with pre-trained models achieves state-of-the-art performance in real-world noisy datasets. Comment: 8 pages, 7 figures |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2205.14299 |
| رقم الأكسشن: | edsarx.2205.14299 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |