[NeurIPS2021] Code Release of Learning Transferable Perturbations

Last update: Nov 11, 2022

Overview

Learning Transferable Adversarial Perturbations

This is an official release of the paper Learning Transferable Adversarial Perturbations. The code is in early release and will be updated by December first week.

Installation

It requires the following OpenMMLab packages:

PyTorch: 1.7.1+cu101
Python: 3.6.9
Torchvision: 0.8.2+cu101
CUDA: 10.1
CUDNN: 7603
NumPy: 1.18.1
PIL: 7.0.0

Download source code from GitHub

 git clone https://github.com/krishnakanthnakka/Transferable_Perturbations.git

Create conda virtual-environment
```
 conda create --name LTP python=3.6.9
```
Activate conda environment
```
 source activate LTP
```
Install requirements
```
 pip install -r requirements.txt
```

Data preparation

The data structure of ImageNet1M looks like below:

/path/to/ImageNet/
├── ImageNet1M
│   ├── train
│   │   ├── n02328150
│   │   ├── n03447447
│   ├── val
│   │   ├── n02328150
│   │   ├── n03447447

Results on ImageNet5K

Train	VGG16	ResNet152	Inceptionv3	DenseNet121	SqueezeNet1.1	ShuffleNet	MNASNet	MobileNet
VGG16	99.32%	68.38%	46.60%	84.68%	86.52%	67.84%	90.44%	60.08%
ResNet152	99.10%	99.72%	74.90%	98.82%	89.12%	96.48%	94.00%	86.44%
SqueezeNet1.1	98.52%	86.67%	75.54%	93.57%	92.47%	89.44%	92.91%	82.75%

Citation

@inproceedings{nakka2021learning,
    title={Learning Transferable Adversarial Perturbations},
    author={Krishna Kanth Nakka and Mathieu Salzmann},
    year={2021},
    booktitle={NeurIPS},
}

[NeurIPS2021] Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks

Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks Code for NeurIPS 2021 Paper "Exploring Architectural Ingredients of A

26 Dec 1, 2022

This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2021, Spotlight)

Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization This codebase is the official implementation of Test-Time Classifier A

47 Dec 28, 2022

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme (NeurIPS2021)

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme (NeurIPS2021) Overview Prerequisites Linux Pytho

34 Mar 31, 2022

PyTorch implementation of Lip to Speech Synthesis with Visual Context Attentional GAN (NeurIPS2021)

Lip to Speech Synthesis with Visual Context Attentional GAN This repository contains the PyTorch implementation of the following paper: Lip to Speech

6 Nov 2, 2022

MAU: A Motion-Aware Unit for Video Prediction and Beyond, NeurIPS2021

MAU (NeurIPS2021) Zheng Chang, Xinfeng Zhang, Shanshe Wang, Siwei Ma, Yan Ye, Xinguang Xiang, Wen GAo. Official PyTorch Code for "MAU: A Motion-Aware

20 Nov 25, 2022

Code release for BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images

BlockGAN Code release for BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images BlockGAN: Learning 3D Object-aware Scene Rep

41 May 18, 2022

Code Release for Learning to Adapt to Evolving Domains

EAML Code release for "Learning to Adapt to Evolving Domains" (NeurIPS 2020) Prerequisites PyTorch = 0.4.0 (with suitable CUDA and CuDNN version) tor

23 Dec 7, 2022

Code release for "Self-Tuning for Data-Efficient Deep Learning" (ICML 2021)

Self-Tuning for Data-Efficient Deep Learning This repository contains the implementation code for paper: Self-Tuning for Data-Efficient Deep Learning

101 Dec 11, 2022

Code release for NeurIPS 2020 paper "Co-Tuning for Transfer Learning"

CoTuning Official implementation for NeurIPS 2020 paper Co-Tuning for Transfer Learning. [News] 2021/01/13 The COCO 70 dataset used in the paper is av

35 Sep 23, 2022

Comments

Pre-trained models on Comics, ChestX, Paintings dataset

Hi @krishnakanthnakka,

We are building our next work on your wonderful NeurIPS paper and were wondering if you could share your pre-trained models (i.e. classifiers you use to train your generators against) on Comics, ChestX, Paintings for comparisons like Table 2. It would keep the comparisons fair and easy to compare with.

Needless to say, we will cite your work and acknowledge the help :)!

opened by abhishekaich27 1

[NeurIPS2021] Code Release of Learning Transferable Perturbations

Related tags

Overview

Learning Transferable Adversarial Perturbations

Installation

Data preparation

Results on ImageNet5K

Citation

You might also like...

[NeurIPS2021] Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks

This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2021, Spotlight)

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme (NeurIPS2021)

PyTorch implementation of Lip to Speech Synthesis with Visual Context Attentional GAN (NeurIPS2021)

MAU: A Motion-Aware Unit for Video Prediction and Beyond, NeurIPS2021

Code release for BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images

Code Release for Learning to Adapt to Evolving Domains

Code release for "Self-Tuning for Data-Efficient Deep Learning" (ICML 2021)

Code release for NeurIPS 2020 paper "Co-Tuning for Transfer Learning"

Comments

Pre-trained models on Comics, ChestX, Paintings dataset

Owner

Krishna Kanth

[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation

Differentiable Optimizers with Perturbations in Pytorch

Code for SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics (ACL'2020).

Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

CLIP: Connecting Text and Image (Learning Transferable Visual Models From Natural Language Supervision)

TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition.

TransPrompt - Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification

LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation (NeurIPS2021 Benchmark and Dataset Track)

Deep Markov Factor Analysis (NeurIPS2021)