Explainability of the Implications of Supervised and Unsupervised Face Image Quality Estimations Through Activation Map Variation Analyses in Face Recognition Models.
Biying FuNaser DamerPublished in: WACV (Workshops) (2022)
Keyphrases
- image quality
- face recognition
- human faces
- face images
- facial images
- unsupervised learning
- image data
- supervised classification
- unsupervised methods
- intra personal
- semi supervised
- supervised methods
- principal component analysis
- recognition rate
- learning algorithm
- supervised learning
- visual quality
- high quality
- face recognition systems