joongsukim

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

pytorch-cifar

95.47% on CIFAR10 with PyTorch

clean-code-python

:bathtub: Clean Code concepts adapted for Python

adversarial-attacks-pytorch

PyTorch implementation of adversarial attacks [torchattacks]

uncertainty-baselines

High-quality implementations of standard and SOTA methods on a variety of tasks.

mixup-cifar10

mixup: Beyond Empirical Risk Minimization

fixmatch

A simple method to perform semi-supervised learning with limited data.

mdistiller

The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf

auto-attack

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

wide-resnet.pytorch

Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch

fast_adversarial

[ICLR 2020] A repository for extremely fast adversarial training using FGSM

Lottery-Ticket-Hypothesis-in-Pytorch

This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" by Jonathan Frankle and Michael Carbin that can be easily adapted to any model/dataset.

Pytorch-Adversarial-Training-CIFAR

This repository provides simple PyTorch implementations for adversarial training methods on CIFAR-10.

semisup-adv

Semisupervised learning for adversarial robustness https://arxiv.org/pdf/1905.13736.pdf

reliability-diagrams

Reliability diagrams visualize whether a classifier model needs calibration

PS-KD-Pytorch

Official PyTorch implementation of PS-KD

DELTA

DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks https://arxiv.org/abs/1901.09229

Adversarial-Information-Bottleneck

[NeurIPS 2021] Official PyTorch Implementation for "Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck"

DLB

Code for Paper "Self-Distillation from the Last Mini-Batch for Consistency Regularization"

mixup.pytorch

an implementation of mixup

DenoisingNet_Adversarial_Training

PyTorch implementation of "Feature Denoising for Improving Adversarial Robustness" on CIFAR10.

fast_advprop

[ICLR 2022]: Fast AdvProp

LBGAT

Learnable Boundary Guided Adversarial Training (ICCV2021)

AdaAD

Code for the paper Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation (CVPR 2023).

SelfSupDefense

hat

Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

DKL

Decoupled Kullback-Leibler Divergence Loss (DKL), NeurIPS 2024

Self-Ensemble-Adversarial-Training

SEAT

RLFAT

Understanding-Robust-Overfitting

Implementation for <Understanding Robust Overftting of Adversarial Training and Beyond> in ICML'22.