Zhou-AY

Sparse-Sharpness-Aware-Minimization

[NeurIPS 2022] Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach -- Official Implementation

pytorch-grad-cam

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Transformer-MM-Explainability

[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

TMM

SVA

Code for the paper "Speckle-Variant Attack: Toward Transferable Adversarial Attack to SAR Target Recognition".

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

VQA

Co-Attack

official PyTorch implement of Towards Adversarial Attack on Vision-Language Pre-training Models

llama

Inference code for Llama models

VisualGLM-6B

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

PandaGPT

[TLLM'23] PandaGPT: One Model To Instruction-Follow Them All

Multimodal-GPT

Multimodal-GPT

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Otter

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

HUST-PhD-Thesis-Latex

华中科技大学博士毕业论文Latex模板

OpenAttack

An Open-Source Package for Textual Adversarial Attack.

SGA

Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]

ALBEF

Code for ALBEF: a new vision-language pre-training method

pytorch-CycleGAN-and-pix2pix

Image-to-Image Translation in PyTorch

ICCV23-Towards-Building-More-Robust-Models-with-Frequency-Bias

[ICCV 2023] Towards Building More Robust Models with Frequency Bias

LAS-AT

Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)

mindarmour

A tool box for MindSpore users to enhance model security and trustworthiness.

Canary_Master

CanarySEFI is a framework for evaluating the robustness of deep learning-based image recognition models. It can evaluate model robustness and attack/defense algorithm effectiveness, encompassing 26 metrics, including 15 models pre-trained by CIFAR-10, CIFAR-100, Fashion-MNIST, and ImageNet (with weights), 20+ attack methods, and 10+ defense methods

ares

A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.

HUST-Invictus

华中科技大学研究生课程资料

adversarial_robustness_pytorch

Unofficial implementation of the DeepMind papers "Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples" & "Fixing Data Augmentation to Improve Adversarial Robustness" in PyTorch

robustbench

RobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]

Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions

Solutions of Reinforcement Learning, An Introduction

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

CFM

[CVPR 2023] Official implementation of the Clean Feature Mixup (CFM) method