Unsupervised Facial Biometric Data Filtering for Age and Gender Estimation
| Autor: | Igor S. Pandžić, Krešimir Bešenić, Jörgen Ahlberg |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Estimation
Computer science business.industry Deep learning Filtering Unsupervised Biometric Web-Scraping Age Gender Data_MISCELLANEOUS Machine learning computer.software_genre Age and gender ComputingMethodologies_PATTERNRECOGNITION Datorseende och robotik (autonoma system) Biometric data Artificial intelligence Biometric Web-Scraping Age Gender business computer Computer Vision and Robotics (Autonomous Systems) |
| Zdroj: | VISIGRAPP (5: VISAPP) Scopus-Elsevier |
| Popis: | Availability of large training datasets was essential for the recent advancement and success of deep learning methods. Due to the difficulties related to biometric data collection, datasets with age and gender annotations are scarce and usually limited in terms of size and sample diversity. Web- scraping approaches for automatic data collection can produce large amounts weakly labeled noisy data. The unsupervised facial biometric data filtering method presented in this paper greatly reduces label noise levels in web-scraped facial biometric data. Experiments on two large state-of-the-art web- scraped facial datasets demonstrate the effectiveness of the proposed method, with respect to training and validation scores, training convergence, and generalization capabilities of trained age and gender estimators. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|