2 citations · 8 across the 22 of their papers we have counts for
23 papers
Revisiting Face Recognition for Monozygotic Twins: The Celeb Twins Test Set
Michael Zang, Haiyu Wu, Mrinal Sharma +1
Past literature on face recognition for monozygotic (("identical") twins points to facial marks and mirror asymmetry as possible directions for improved accuracy of twins recogniti…
VIScore: Diagnosing Planning-Relevant Quality in Latent World Models
Haiyu Wu, Randall Balestriero, Morgan Levine
Regulating the latent space to an isotropic Gaussian distribution provides a stable and information-maximized landscape for world model planning. However, the latent space property…
ScaleErasure: Inference-Time Minimal Intervention for Precise Concept Erasure in Next-Scale Autoregressive Image Generation
Cong Wang, Haiyu Wu, Zhiwei Jiang +4
Concept erasure aims to prevent image generative models from producing unsafe content while preserving their general generative capability. Meanwhile, next-scale autoregressive (AR…
VISReg: Variance-Invariance-Sketching Regularization for JEPA training
Haiyu Wu, Randall Balestriero, Morgan Levine
Self-supervised learning methods prevent embedding collapse via modeling heuristics or explicit regularization of the embedding space. Among the latter, VICReg decomposes regulariz…
Restricted Receptive Fields for Face Verification
Kagan Ozturk, Aman Bhatta, Haiyu Wu +2
Understanding how deep neural networks make decisions is crucial for analyzing their behavior and diagnosing failure cases. In computer vision, a common approach to improve interpr…
Vec2Face+ for Face Dataset Generation
Haiyu Wu, Jaskirat Singh, Sicong Tian +2
When synthesizing identities as face recognition training data, it is generally believed that large inter-class separability and intra-class attribute variation are essential for s…
Lights, Camera, Matching: The Role of Image Illumination in Fair Face Recognition
Gabriella Pangelinan, Grace Bezold, Haiyu Wu +2
Facial brightness is a key image quality factor impacting face recognition accuracy differentials across demographic groups. In this work, we aim to decrease the accuracy gap betwe…
On the Illusion of Gender Bias in Face Recognition: Explaining the Fairness Issue Through Non-demographic Attributes
Paul Jonas Kurz, Haiyu Wu, Rouqaiah Al-Refai +2
Face recognition systems (FRS) exhibit significant accuracy differences based on the user's gender. Since such a gender gap reduces the trustworthiness of FRS, more recent efforts…
Impact of Sunglasses on One-to-Many Facial Identification Accuracy
Sicong Tian, Haiyu Wu, Michael C. King +1
One-to-many facial identification is documented to achieve high accuracy in the case where both the probe and the gallery are "mugshot quality" images. However, an increasing numbe…
Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors
Haiyu Wu, Jaskirat Singh, Sicong Tian +2
This paper studies how to synthesize face images of non-existent persons, to create a dataset that allows effective training of face recognition (FR) models. Besides generating rea…
Can the accuracy bias by facial hairstyle be reduced through balancing the training data?
Kagan Ozturk, Haiyu Wu, Kevin W. Bowyer
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…
Identity Overlap Between Face Recognition Train/Test Data: Causing Optimistic Bias in Accuracy Measurement
Haiyu Wu, Sicong Tian, Jacob Gutierrez +3
A fundamental tenet of pattern recognition is that overlap between training and testing sets causes an optimistic accuracy estimate. Deep CNNs for face recognition are trained for…
Goldilocks Test Sets for Face Verification
Haiyu Wu, Sicong Tian, Aman Bhatta +6
Reported face verification accuracy has reached a plateau on current well-known test sets. As a result, some difficult test sets have been assembled by reducing the image quality o…
CRAFT: Contextual Re-Activation of Filters for face recognition Training
Aman Bhatta, Domingo Mery, Haiyu Wu +1
The first layer of a deep CNN backbone applies filters to an image to extract the basic features available to later layers. During training, some filters may go inactive, mean ing…
LogicNet: A Logical Consistency Embedded Face Attribute Learning Network
Haiyu Wu, Sicong Tian, Huayu Li +1
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…
What's color got to do with it? Face recognition in grayscale
Aman Bhatta, Domingo Mery, Haiyu Wu +3
State-of-the-art deep CNN face matchers are typically created using extensive training sets of color face images. Our study reveals that such matchers attain virtually identical ac…
Beard Segmentation and Recognition Bias
Kagan Ozturk, Grace Bezold, Aman Bhatta +2
A person's facial hairstyle, such as presence and size of beard, can significantly impact face recognition accuracy. There are publicly-available deep networks that achieve reasona…
What Should Be Balanced in a "Balanced" Face Recognition Dataset?
Haiyu Wu, Kevin W. Bowyer
The issue of demographic disparities in face recognition accuracy has attracted increasing attention in recent years. Various face image datasets have been proposed as 'fair' or 'b…
Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning
Haiyu Wu, Grace Bezold, Aman Bhatta +1
Face attribute research has so far used only simple binary attributes for facial hair; e.g., beard / no beard. We have created a new, more descriptive facial hair annotation scheme…
Face Recognition Accuracy Across Demographics: Shining a Light Into the Problem
Haiyu Wu, Vítor Albiero, K. S. Krishnapriya +2
We explore varying face recognition accuracy across demographic groups as a phenomenon partly caused by differences in face illumination. We observe that for a common operational s…
Towards Boosting the Channel Attention in Real Image Denoising : Sub-band Pyramid Attention
Huayu Li, Haiyu Wu, Xiwen Chen +2
Convolutional layers in Artificial Neural Networks (ANN) treat the channel features equally without feature selection flexibility. While using ANNs for image denoising in real-worl…
Research on All-content Text Recognition Method for Financial Ticket Image
Fukang Tian, Haiyu Wu, Bo Xu
With the development of the economy, the number of financial tickets increases rapidly. The traditional manual invoice reimbursement and financial accounting system bring more and…
Financial ticket intelligent recognition system based on deep learning
Fukang Tian, Haiyu Wu, Bo Xu
Facing the rapid growth in the issuance of financial tickets (or bills, invoices etc.), traditional manual invoice reimbursement and financial accounting system are imposing an inc…