hanwei0912

Adversarial-Reading

Paper sharing in adversary related works

Adversarial-Training-for-Free

Unofficial implementation of the paper 'Adversarial Training for Free'

DDN-attack

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

Interpretability-methods-for-self-supervised-and-supervised-models

In recent years, the rapid development of Deep Neural Networks (DNN) has led to a remarkable performance in many complex tasks in the field of computer vision at the cost of the models’ complexity. The more complex the models get, the higher the need is for understanding them. The primary objective of this repo is to give visual explanations on what both supervised and self-supervised methods really learn during training. Self-supervised and supervised state-of-the-art pre-trained models will be investigated. As backbone networks, for both categories convnets and Transformers based architectures will be used. Variation of visualization techniques will be used.

NMS

Accelerating MOEA/D by Nelder-Mead method

OptiCAM

code for the paper: "Opti-CAM: Optimizing saliency maps for interpretability"

SmoothAdversarialExamples

Smooth Adversarial Examples

Tree-structured-decomposition-and-adaptation-in-moea-d

Tree-structured decomposition and adaptation in moea/d

walking-on-the-edge-fast-low-distortion-adversarial-examples

Walking on the Edge: Fast, Low-Distortion Adversarial Examples

hanwei0912/Adversarial-Reading

Paper sharing in adversary related works

hanwei0912/walking-on-the-edge-fast-low-distortion-adversarial-examples

Walking on the Edge: Fast, Low-Distortion Adversarial Examples

hanwei0912/SmoothAdversarialExamples

Smooth Adversarial Examples

hanwei0912/OptiCAM

code for the paper: "Opti-CAM: Optimizing saliency maps for interpretability"

hanwei0912/DDN-attack

hanwei0912/Interpretability-methods-for-self-supervised-and-supervised-models

In recent years, the rapid development of Deep Neural Networks (DNN) has led to a remarkable performance in many complex tasks in the field of computer vision at the cost of the models’ complexity. The more complex the models get, the higher the need is for understanding them. The primary objective of this repo is to give visual explanations on what both supervised and self-supervised methods really learn during training. Self-supervised and supervised state-of-the-art pre-trained models will be investigated. As backbone networks, for both categories convnets and Transformers based architectures will be used. Variation of visualization techniques will be used.

hanwei0912/NMS

Accelerating MOEA/D by Nelder-Mead method

hanwei0912/Tree-structured-decomposition-and-adaptation-in-moea-d

Tree-structured decomposition and adaptation in moea/d

hanwei0912/Adversarial-Training-for-Free

Unofficial implementation of the paper 'Adversarial Training for Free'

hanwei0912/dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

hanwei0912/foolbox

Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, Keras, …

hanwei0912/hanwei0912.github.io

Hanwei | Homepage

hanwei0912/jMetalPy

A framework for single/multi-objective optimization with metaheuristics

hanwei0912/knn-defense

Defending Against Adversarial Examples with K-Nearest Neighbor

hanwei0912/MathSTIC-UBL

Doctoral Thesis Class for the MathSTIC Doctoral School / Université Bretagne Loire

hanwei0912/Quantus

Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations

hanwei0912/zutils