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 • 19 Nov 2023 • Haiyu Wu, Sicong Tian, Huayu Li, Kevin W. Bowyer
We explore the potential reasons for this oversight and introduce two pressing challenges to the field: 1) How can we ensure that a model, when trained with data checked for logical consistency, yields predictions that are logically consistent?
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 • 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 • 17 Apr 2023 • Haiyu Wu, Kevin W. Bowyer
These datasets typically balance the number of identities and images across demographics.
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.
1 code implementation • 13 Oct 2022 • Haiyu Wu, Grace Bezold, Manuel Günther, Terrance Boult, Michael C. King, Kevin W. Bowyer
Two annotators independently assigning attribute values shows that only 12 of 40 common attributes are assigned values with >= 95% consistency, and three (high cheekbones, pointed nose, oval face) have essentially random consistency.
3 code implementations • 4 Jun 2022 • Haiyu Wu, Vítor Albiero, K. S. Krishnapriya, Michael C. King, Kevin W. Bowyer
This is the first work that we are aware of to explore how the level of brightness of the skin region in a pair of face images (rather than a single image) impacts face recognition accuracy, and to evaluate this as a systematic factor causing unequal accuracy across demographics.
no code implementations • 5 Jan 2021 • Fukang Tian, Haiyu Wu, Bo Xu
At present, a few works have applied deep learning methods to financial ticket recognition.
no code implementations • 23 Dec 2020 • Huayu Li, Haiyu Wu, Xiwen Chen, Hanning Zhang, Abolfazl Razi
We equip the SPA blocks on a network designed for real image denoising.
no code implementations • 15 Dec 2020 • Fukang Tian, Haiyu Wu, Bo Xu
With the development of the economy, the number of financial tickets increases rapidly.
no code implementations • 29 Oct 2020 • Fukang Tian, Haiyu Wu, Bo Xu
Facing the rapid growth in the issuance of financial tickets (or bills, invoices etc.
1 code implementation • 25 Apr 2020 • Huayu Li, Xiwen Chen, Haiyu Wu, Zaoyi Chi, Christopher Mann, Abolfazl Razi
Recently, end-to-end deep learning-based methods have been utilized to reconstruct the object wavefront (as a surrogate for the 3D structure of the object) directly from a single-shot in-line digital hologram.