Meta Soft Label Generation for Noisy Labels
| Autor: | Görkem Algan, Ilkay Ulusoy |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Machine Learning (stat.ML) 02 engineering and technology 010501 environmental sciences 01 natural sciences Machine Learning (cs.LG) Margin (machine learning) Statistics - Machine Learning Classifier (linguistics) 0202 electrical engineering electronic engineering information engineering Code (cryptography) 0105 earth and related environmental sciences Training set Artificial neural network business.industry Pattern recognition Base (topology) Pattern recognition (psychology) Deep neural networks 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | ICPR |
| DOI: | 10.48550/arxiv.2007.05836 |
| Popis: | The existence of noisy labels in the dataset causes significant performance degradation for deep neural networks (DNNs). To address this problem, we propose a Meta Soft Label Generation algorithm called MSLG, which can jointly generate soft labels using meta-learning techniques and learn DNN parameters in an end-to-end fashion. Our approach adapts the meta-learning paradigm to estimate optimal label distribution by checking gradient directions on both noisy training data and noise-free meta-data. In order to iteratively update soft labels, meta-gradient descent step is performed on estimated labels, which would minimize the loss of noise-free meta samples. In each iteration, the base classifier is trained on estimated meta labels. MSLG is model-agnostic and can be added on top of any existing model at hand with ease. We performed extensive experiments on CIFAR10, Clothing1M and Food101N datasets. Results show that our approach outperforms other state-of-the-art methods by a large margin. Comment: Accepted by ICPR 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|