Search Results for author:
Found 8 papers, 2 papers with code
What is a Goldilocks Face Verification Test Set?
We show that current train and test sets are generally not identity- or even image-disjoint, and that this results in an optimistic bias in the estimated accuracy.
Identity Overlap Between Face Recognition Train/Test Data: Causing Optimistic Bias in Accuracy Measurement
In particular, our experiments reveal a surprising degree of identity and image overlap between the LFW family of test sets and the MS1MV2 training set.
CRAFT: Contextual Re-Activation of Filters for face recognition Training
We show that CRAFT reduces fraction of inactive filters from 44% to 32% on average and discovers filter patterns not found by standard training.
Our Deep CNN Face Matchers Have Developed Achromatopsia
We show that such matchers achieve essentially the same accuracy on the grayscale or the color version of a set of test images.
Impact of Blur and Resolution on Demographic Disparities in 1-to-Many Facial Identification
This paper analyzes the accuracy of 1-to-many facial identification across demographic groups, and in the presence of blur and reduced resolution in the probe image as might occur in "surveillance camera quality" images.
Beard Segmentation and Recognition Bias
To investigate the effect of facial hair in a rigorous manner, we first created a set of fine-grained facial hair annotations to train a segmentation model and evaluate its accuracy across African-American and Caucasian face images.
Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning
We propose a logically consistent prediction loss, LCPLoss, to aid learning of logical consistency across attributes, and also a label compensation training strategy to eliminate the problem of no positive prediction across a set of related attributes.
The Gender Gap in Face Recognition Accuracy Is a Hairy Problem
We then demonstrate that when the data used to estimate recognition accuracy is balanced across gender for how hairstyles occlude the face, the initially observed gender gap in accuracy largely disappears.
