An analysis of the robustness of deep face recognition networks to noisy training labels
| Autor: | Christopher Reale, Rama Chellappa, Nasser M. Nasrabadi |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Training set
Noise measurement Computer science business.industry media_common.quotation_subject education 0211 other engineering and technologies Fidelity 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Convolutional neural network Facial recognition system ComputingMethodologies_PATTERNRECOGNITION Robustness (computer science) Artificial intelligence business computer 021101 geological & geomatics engineering 0105 earth and related environmental sciences media_common |
| Zdroj: | GlobalSIP |
| DOI: | 10.1109/globalsip.2016.7906030 |
| Popis: | In recent years, state-of-the-art face recognition performance has improved by using deep convolutional neural networks. One disadvantage of these methods is their need for very large, labeled training datasets as collecting and labeling them can be time consuming and prone to error. In this work we examine the robustness of a convolutional neural network to limited training data and training data with noisy labels. We train face recognition networks with varying training set sizes and varying amounts of mislabeled samples. Our experiments show data fidelity is significantly more important than training set size; decreasing the percentage of correctly labeled samples by ten is approximately equivalent to halving the number of training samples. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|