Shihua Huang's repositories
deepmind_adversarial_robustness
This is a copy of deepmind's adversarial robustness repo
adversarial-attacks-pytorch
PyTorch implementation of adversarial attacks.
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
AWP
Codes for NeurIPS 2020 paper "Adversarial Weight Perturbation Helps Robust Generalization"
CelebA
dataset
DCNv2
Deformable Convolutional Networks v2 with Pytorch
DDRNet.pytorch
This is the unofficial code of Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. which achieve state-of-the-art trade-off between accuracy and speed on cityscapes and camvid, without using inference acceleration and extra data
Efficient-AI-Backbones
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
mmdetection
OpenMMLab Detection Toolbox and Benchmark
mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
moco
PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
nsga-net
NSGA-Net, a Neural Architecture Search Algorithm
once-for-all
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
poolformer-1
PoolFormer: MetaFormer is Actually What You Need for Vision
pytorch-cifar
95.47% on CIFAR10 with PyTorch
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
ResNeXt.pytorch
Reproduces ResNet-V3 with pytorch
robust-residual-network
Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective
robustbench
RobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]
segmentation_models.pytorch
Segmentation models with pretrained backbones. PyTorch.
ShihuaHuang95.github.io
Shihua Huang's home page
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
ViTs-vs-CNNs
[NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)