Downloads · 30 days
0
robust-imagenet-models
madrylab/robust-imagenet-models
robust-imagenet-models is a machine learning model from madrylab. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository contains the robust ImageNet models used in our paper "Do adversarially robust imagenet models transfer better?".
Access
Public
Updated Jul 7, 2023
Repo size
34.7 GB
Likes
5
Public
Repo makeup
Click a slice to open those files.
.ckpt34.7 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Jul 7, 2023
- Updated
- Jul 7, 2023
- SHA
- 1c68d6e1
Model card
From the Hugging Face model README
Overview
This repository contains the robust ImageNet models used in our paper "Do adversarially robust imagenet models transfer better?".
See our papers's GitHub repository for more details!
Summary of our pretrained models
Standard Accuracy of L2-Robust ImageNet Models
| Model | ε=0 | ε=0.01 | ε=0.03 | ε=0.05 | ε=0.1 | ε=0.25 | ε=0.5 | ε=1.0 | ε=3.0 | ε=5.0 |
|---|---|---|---|---|---|---|---|---|---|---|
| ResNet-18 | 69.79 | 69.90 | 69.24 | 69.15 | 68.77 | 67.43 | 65.49 | 62.32 | 53.12 | 45.59 |
| ResNet-50 | 75.80 | 75.68 | 75.76 | 75.59 | 74.78 | 74.14 | 73.16 | 70.43 | 62.83 | 56.13 |
| Wide-ResNet-50-2 | 76.97 | 77.25 | 77.26 | 77.17 | 76.74 | 76.21 | 75.11 | 73.41 | 66.90 | 60.94 |
| Wide-ResNet-50-4 | 77.91 | 78.02 | 77.87 | 77.77 | 77.64 | 77.10 | 76.52 | 75.51 | 69.67 | 65.20 |
| Model | ε=0 | ε=3 |
|---|---|---|
| DenseNet | 77.37 | 66.98 |
| MNASNET | 60.97 | 41.83 |
| MobileNet-v2 | 65.26 | 50.40 |
| ResNeXt50_32x4d | 77.38 | 66.25 |
| ShuffleNet | 64.25 | 43.32 |
| VGG16_bn | 73.66 | 57.19 |
Standard Accuracy of Linf-Robust ImageNet Models
- License
- mit
- Created
- Jul 7, 2023
- Updated
- Jul 7, 2023