1 code implementation • 24 May 2024 • Haiyu Wu, Sicong Tian, Aman Bhatta, Jacob Gutierrez, Grace Bezold, Genesis Argueta, Karl Ricanek Jr., Michael C. King, Kevin W. Bowyer
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.
no code implementations • 15 May 2024 • Haiyu Wu, Sicong Tian, Jacob Gutierrez, Aman Bhatta, Kağan Öztürk, Kevin W. Bowyer
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.
no code implementations • 29 Nov 2023 • Aman Bhatta, Domingo Mery, Haiyu Wu, Kevin W. Bowyer
We show that CRAFT reduces fraction of inactive filters from 44% to 32% on average and discovers filter patterns not found by standard training.
no code implementations • 11 Sep 2023 • Aman Bhatta, Domingo Mery, Haiyu Wu, Joyce Annan, Micheal C. King, Kevin W. Bowyer
We show that such matchers achieve essentially the same accuracy on the grayscale or the color version of a set of test images.
no code implementations • 8 Sep 2023 • Aman Bhatta, Gabriella Pangelinan, Michael C. King, Kevin W. Bowyer
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.
no code implementations • 30 Aug 2023 • Kagan Ozturk, Grace Bezold, Aman Bhatta, Haiyu Wu, Kevin Bowyer
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.
1 code implementation • CVPR 2023 • Haiyu Wu, Grace Bezold, Aman Bhatta, Kevin W. Bowyer
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.
no code implementations • 10 Jun 2022 • Aman Bhatta, Vítor Albiero, Kevin W. Bowyer, Michael C. King
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.