Haibin Zheng's repositories
NeuronFair
Interpretable White-Box Fairness Testing through Biased Neuron Identification
physical-attack
Physical attack on face, license plate and road sign recognition system
fashion-mnist
A MNIST-like fashion product database. Benchmark :point_right:
AdversarialAttack-FineFool
FineFool: Fine Object Contour Attack via Attention, an adversarial attack method combined with attention mechanism
AIF360
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
awesome-automl-papers
A curated list of automated machine learning papers, articles, tutorials, slides and projects
CaseRecommender
Case Recommender: A Flexible and Extensible Python Framework for Recommender Systems
fairlearn
A Python package to assess and improve fairness of machine learning models.
fairness-indicators
Tensorflow's Fairness Evaluation and Visualization Toolkit
GONE
We propose GONE, a Generic O(1) NoisE layer added behind any DNNs’ output layer at the inference stage.
inversecooking
Recipe Generation from Food Images
prioritize_PRIMA
This is the implementation repository of our ICSE 2021 paper: Prioritizing Test Inputs for Deep Neural Networks via Mutation Analysis.
Reverse-Cross-Entropy
Reverse Cross Entropy Training for Adversarial Detection (NeurIPS 2018)
rosita
ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration
tensorflow
An Open Source Machine Learning Framework for Everyone
tpu
Reference models and tools for Cloud TPUs.
umap
Uniform Manifold Approximation and Projection
VidVRD-helper
Video Visual Relation Detection