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

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 a…

Reliability diagrams visualize whether a classifier model needs calibration

95.47% on CIFAR10 with PyTorch

an implementation of mixup

mixup: Beyond Empirical Risk Minimization

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

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

Learnable Boundary Guided Adversarial Training (ICCV2021)

PyTorch implementation of adversarial attacks [torchattacks]

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

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

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…

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

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

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

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

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

Official PyTorch implementation of PS-KD

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

SEAT

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

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

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

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

[ICLR 2022]: Fast AdvProp

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

🛁 Clean Code concepts adapted for Python