Zhang Peixin's repositories
Aequitas-1
Aequitas, a directed fairness testing framework machine learning models.
auto_LiRPA
[NeurIPS 2020]auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks
deep-transfer-learning
A collection of implementations of deep domain adaptation algorithms
face-classification
Face model to classify gender and race. Trained on LFWA+ Dataset.
face.evoLVe.PyTorch
🔥🔥High-Performance Face Recognition Library on PyTorch🔥🔥
FacialPhenotypes
Face Verification and Identification Test Code for Racial Phenotype Evaluation on RFW and VGGFace2
insightface
Face Analysis Project on MXNet and PyTorch
nlp_adversarial_examples
Implementation code for the paper "Generating Natural Language Adversarial Examples"
pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch
recommenders
Best Practices on Recommendation Systems
TOG
Real-time object detection is one of the key applications of deep neural networks (DNNs) for real-world mission-critical systems. While DNN-powered object detection systems celebrate many life-enriching opportunities, they also open doors for misuse and abuse. This project presents a suite of adversarial objectness gradient attacks, coined as TOG,
VGG1200-Races
Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation
zjuthesis-1
Zhejiang University Graduation Thesis LaTeX Template