Our deep cnn face matchers have developed achromatopsia
Modern deep CNN face matchers are trained on datasets containing" color" images. We
show that such matchers achieve essentially the same accuracy on color images when …
show that such matchers achieve essentially the same accuracy on color images when …
Facial hair area in face recognition across demographics: Small size, big effect
Observed variations in face recognition accuracy across demographics, often viewed as"
bias", have motivated research into the causes of such variations. Variations in facial …
bias", have motivated research into the causes of such variations. Variations in facial …
Can the accuracy bias by facial hairstyle be reduced through balancing the training data?
Appearance of a face can be greatly altered by growing a beard and mustache. The facial
hairstyles in a pair of images can cause marked changes to the impostor distribution and the …
hairstyles in a pair of images can cause marked changes to the impostor distribution and the …
LogicNet: A Logical Consistency Embedded Face Attribute Learning Network
Ensuring logical consistency in predictions is a crucial yet overlooked aspect in multi-
attribute classification. We explore the potential reasons for this oversight and introduce two …
attribute classification. We explore the potential reasons for this oversight and introduce two …