Code of paper: "DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks"

Overview

image

GitHub GitHub Repo stars GitHub Repo stars

DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks

Abstract: Adversarial training has been proven to be a powerful regularization method to improve generalization of models. In this work, a novel masked weight adversarial training method, DropAttack, is proposed for improving generalization potential of neural network models. It enhances the coverage and diversity of adversarial attack by intentionally adding worst-case adversarial perturbations to both the input and hidden layers and randomly masking the attack perturbations on a certain proportion weight parameters. It then improves the generalization of neural networks by minimizing the internal adversarial risk generated by exponentially different attack combinations. Further, the method is a general technique that can be adopted to a wide variety of neural networks with different architectures. To validate the effectiveness of the proposed method, five public datasets were used in the fields of natural language processing (NLP) and computer vision (CV) for experimental evaluating. This study compared DropAttack with other adversarial training methods and regularization methods. It was found that the proposed method achieves state-of-the-art performance on all datasets. In addition, the experimental results of this study show that DropAttack method can achieve similar performance when it uses only a half training data required in standard training. Theoretical analysis revealed that DropAttack can perform gradient regularization at random on some of the input and weight parameters of the model. Further, visualization experiments of this study show that DropAttack can push the minimum risk of the neural network model to a lower and flatter loss landscapes.

  • For technical details and additional experimental results, please refer to our paper:

“DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks”

image

  • Experimental results:

image

image

DropAttack indeed selects flatter loss landscapes via masked adversarial perturbations.

[The code of loss visualization] image

  • Citation

@article{ni2021dropattack,
  title={DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks},
  author={Ni, Shiwen and Li, Jiawen and Kao, Hung-Yu},
  journal={arXiv preprint arXiv:2108.12805},
  year={2021}
}
  • Requirements

pytorch
pandas
numpy
nltk
sklearn
torchtext
  • Please star it, thank you! :)

You might also like...
PyTorch code for the paper: FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning
PyTorch code for the paper: FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning This is the PyTorch implementation of our paper: FeatMatch: Feature-Based Augmentat

Code for the paper A Theoretical Analysis of the Repetition Problem in Text Generation
Code for the paper A Theoretical Analysis of the Repetition Problem in Text Generation

A Theoretical Analysis of the Repetition Problem in Text Generation This repository share the code for the paper "A Theoretical Analysis of the Repeti

Code for our ICASSP 2021 paper: SA-Net: Shuffle Attention for Deep Convolutional Neural Networks
Code for our ICASSP 2021 paper: SA-Net: Shuffle Attention for Deep Convolutional Neural Networks

SA-Net: Shuffle Attention for Deep Convolutional Neural Networks (paper) By Qing-Long Zhang and Yu-Bin Yang [State Key Laboratory for Novel Software T

Open source repository for the code accompanying the paper 'Non-Rigid Neural Radiance Fields Reconstruction and Novel View Synthesis of a Deforming Scene from Monocular Video'.
Open source repository for the code accompanying the paper 'Non-Rigid Neural Radiance Fields Reconstruction and Novel View Synthesis of a Deforming Scene from Monocular Video'.

Non-Rigid Neural Radiance Fields This is the official repository for the project "Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synt

Code for the Shortformer model, from the paper by Ofir Press, Noah A. Smith and Mike Lewis.

Shortformer This repository contains the code and the final checkpoint of the Shortformer model. This file explains how to run our experiments on the

PyTorch code for ICLR 2021 paper Unbiased Teacher for Semi-Supervised Object Detection
PyTorch code for ICLR 2021 paper Unbiased Teacher for Semi-Supervised Object Detection

Unbiased Teacher for Semi-Supervised Object Detection This is the PyTorch implementation of our paper: Unbiased Teacher for Semi-Supervised Object Detection

Official code for paper "Optimization for Oriented Object Detection via Representation Invariance Loss".

Optimization for Oriented Object Detection via Representation Invariance Loss By Qi Ming, Zhiqiang Zhou, Lingjuan Miao, Xue Yang, and Yunpeng Dong. Th

Code for our CVPR 2021 paper
Code for our CVPR 2021 paper "MetaCam+DSCE"

Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification (CVPR'21) Introduction Code for our CVPR 2021

Code for our CVPR2021 paper coordinate attention
Code for our CVPR2021 paper coordinate attention

Coordinate Attention for Efficient Mobile Network Design (preprint) This repository is a PyTorch implementation of our coordinate attention (will appe

Owner
倪仕文 (Shiwen Ni)
PhD candidate in Computer Science (ML&NLP)
倪仕文 (Shiwen Ni)
Code for paper ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop.

Who Left the Dogs Out? Evaluation and demo code for our ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization

Benjamin Biggs 26 Jul 30, 2022
This is the official source code for SLATE. We provide the code for the model, the training code, and a dataset loader for the 3D Shapes dataset. This code is implemented in Pytorch.

SLATE This is the official source code for SLATE. We provide the code for the model, the training code and a dataset loader for the 3D Shapes dataset.

Gautam Singh 58 Sep 17, 2022
TensorFlow code for the neural network presented in the paper: "Structural Language Models of Code" (ICML'2020)

SLM: Structural Language Models of Code This is an official implementation of the model described in: "Structural Language Models of Code" [PDF] To ap

null 70 Sep 21, 2022
Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".

CoProtector Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".

Zhensu Sun 1 Oct 26, 2021
Code to use Augmented Shapiro Wilks Stopping, as well as code for the paper "Statistically Signifigant Stopping of Neural Network Training"

This codebase is being actively maintained, please create and issue if you have issues using it Basics All data files are included under losses and ea

J K Terry 32 Nov 9, 2021
Code for our method RePRI for Few-Shot Segmentation. Paper at http://arxiv.org/abs/2012.06166

Region Proportion Regularized Inference (RePRI) for Few-Shot Segmentation In this repo, we provide the code for our paper : "Few-Shot Segmentation Wit

Malik Boudiaf 132 Sep 11, 2022
Code for ACM MM 2020 paper "NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination"

NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination The offical implementation for the "NOH-NMS: Improving Pedestrian Detection by

Tencent YouTu Research 63 Sep 22, 2022
Official TensorFlow code for the forthcoming paper

~ Efficient-CapsNet ~ Are you tired of over inflated and overused convolutional neural networks? You're right! It's time for CAPSULES :)

Vittorio Mazzia 189 Sep 15, 2022
This is the code for the paper "Contrastive Clustering" (AAAI 2021)

Contrastive Clustering (CC) This is the code for the paper "Contrastive Clustering" (AAAI 2021) Dependency python>=3.7 pytorch>=1.6.0 torchvision>=0.8

Yunfan Li 192 Sep 14, 2022
Code for the paper Learning the Predictability of the Future

Learning the Predictability of the Future Code from the paper Learning the Predictability of the Future. Website of the project in hyperfuture.cs.colu

Computer Vision Lab at Columbia University 138 Sep 15, 2022