joongsukim

joongsukim's Stars

• karpathy/nanoGPT

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

  Language:Python36.2k5.7k

• rahulvigneswaran/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.

  Language:Python32192

• hollance/reliability-diagrams

  Reliability diagrams visualize whether a classifier model needs calibration

  Language:Jupyter Notebook13417

• kuangliu/pytorch-cifar

  95.47% on CIFAR10 with PyTorch

  Language:Python5.9k2.1k

• moskomule/mixup.pytorch

  an implementation of mixup

  Language:Python417

• facebookresearch/mixup-cifar10

  mixup: Beyond Empirical Risk Minimization

  Language:Python1.2k225

• Meta-knowledge-Lab/DLB

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

  Language:Python414

• jiequancui/DKL

  Decoupled Kullback-Leibler Divergence Loss (DKL)

  Language:Python213

• dvlab-research/LBGAT

  Learnable Boundary Guided Adversarial Training (ICCV2021)

  Language:Python332

• Harry24k/adversarial-attacks-pytorch

  PyTorch implementation of adversarial attacks [torchattacks]

  Language:Python1.8k345

• boyellow/AdaAD

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

  Language:Python292

• bmsookim/wide-resnet.pytorch

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

  Language:Python457129

• megvii-research/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

  Language:Python787119

• google/uncertainty-baselines

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

  Language:Python1.4k202

• lixingjian/DELTA

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

  Language:Python6612

• cvlab-columbia/SelfSupDefense

  Language:Python285

• JHL-HUST/RLFAT

  Language:Python133

• ByungKwanLee/Adversarial-Information-Bottleneck

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

  Language:Python452

• A-LinCui/DenoisingNet_Adversarial_Training

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

  Language:Python355

• ChaojianYu/Understanding-Robust-Overfitting

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

  Language:Python121

• lgcnsai/PS-KD-Pytorch

  Official PyTorch implementation of PS-KD

  Language:Python8214

• imrahulr/hat

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

  Language:Python295

• whj363636/Self-Ensemble-Adversarial-Training

  SEAT

  Language:Python193

• yaircarmon/semisup-adv

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

  Language:Python13615

• fra31/auto-attack

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

  Language:Python642111

• google-research/fixmatch

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

  Language:Python1.1k172

• locuslab/fast_adversarial

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

  Language:Python42293

• meijieru/fast_advprop

  [ICLR 2022]: Fast AdvProp

  Language:Python35

• ndb796/Pytorch-Adversarial-Training-CIFAR

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

  Language:Python15137

• zedr/clean-code-python

  :bathtub: Clean Code concepts adapted for Python

  Language:Python4.4k770