EMP325's repositories
ANL
Code for "Adversarial Noise Layer: Regularize Neural Network By Adding Noise"
deep-learning-for-image-processing
deep learning for image processing including classification and object-detection etc.
GAM
The official repo for CVPR2023 highlight paper "Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization".
WSAM
WSAM
tied-augment
Tied-Augment: Controlling Representation Similarity Improves Data Augmentation
PyHessian
PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks
O2U-Net
paper "O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural Networks" code
YOLOv4-pytorch
This is a pytorch repository of YOLOv4, attentive YOLOv4 and mobilenet YOLOv4 with PASCAL VOC and COCO
TWA
Trainable Weight Averaging for Fast Convergence and Better Generalization
RMSGD
Exploiting Explainable Metrics for Augmented SGD [CVPR2022]
GSAM
PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)
sam
SAM: Sharpness-Aware Minimization (PyTorch)
PAC-Bayes-IB
Official repo for PAC-Bayes Information Bottleneck.
TRADES
TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)
awesome-latex-cv
Latex CV template built with Font Awesome.
ASAM
Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.
AdversaryLossLandscape
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Adabelief-Optimizer
Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"
AMP-Regularizer
Code for our paper "Regularizing Neural Networks via Adversarial Model Perturbation", CVPR2021
pytorch-cifar100
Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)
Friendly-Adversarial-Training
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger (ICML2020 Paper)
uncertainty-baselines
High-quality implementations of standard and SOTA methods on a variety of tasks.