Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)

PyTorch-1.0 implementation for the adversarial training on MNIST/CIFAR-10 and visualization on robustness classifier.

Language-Adversarial Training for Cross-Lingual Text Classification (TACL)

Feature Scattering Adversarial Training

Understanding and Improving Fast Adversarial Training [Jul 2020]

Semi-supervised adversarial neural networks for classification of single cell transcriptomics data

Pytorch-Named-Entity-Recognition-with-transformers

Code for the paper "Addressing Model Vulnerability to Distributional Shifts over Image Transformation Sets", ICCV 2019

Tensorflow deep learning based domain adaptation model implementations with experiment of estimate MNIST by SVHN data (SVHN -> MNIST): DANN (domain-adversarial neural network), Deep JDOT (joint distribution optimal transportation)

Ensemble Adversarial Black-Box Attacks against Deep Learning Systems Trained by MNIST, USPS and GTSRB Datasets

Chainer implementation of Bayesian Convolutional Neural Networks (BCNNs)

Domain Adaptation with Adversarial Training and Graph Embeddings

Code for paper "Model-based Adversarial Meta-Reinforcement Learning" (https://arxiv.org/abs/2006.08875)

Unsupervised Domain Adaptation for Acoustic Scene Classification with Wasserstein Distance

Chapter 11: Transfer Learning/Domain Adaptation

Migrate to PyTorch. Re-implementation of Bayesian Convolutional Neural Networks (BCNNs)

some paper of Knowledge Distillation and Adversarial Training about NLP

Code for the paper: Adversarial Training against Location-Optimized Adversarial Patches. ECCV CVCOPS 2020 (to appear)

Retinal lesions segmentation using CNNs and adversarial training: A Degree Thesis Submitted to the Faculty of Escola Tècnica d’Enginyeria de Telecomunicació de Barcelona of Universitat Politècnica de Catalunya.

Experiments with distributionally robust optimization (DRO) for deep neural networks

Analyzing Conditional Adversarial Networks to solve image recovery problems like shadow recovery, denoising and deblurring - CVIP 2019

nips2018 vision adversarial robustness competition - model track 2nd place solution

Shows how to create basic image adversaries, and train adversarially robust image classifiers (to some extent).

Implementation of adversarial training under fast-gradient sign method (FGSM), projected gradient descent (PGD) and CW using Wide-ResNet-28-10 on cifar-10. Sample code is re-usable despite changing the model or dataset.

A short literature review on how neural networks are easily fooled.

WideResNet implementation on MNIST dataset. FGSM and PGD adversarial attacks on standard training, PGD adversarial training, and Feature Scattering adversarial training.