| Architecture | Auxiliary Classifier, Average Pooling, 1x1 Convolution, Average Pooling, Batch Normalization, Convolution, Dropout, Dense Connections, Inception-v3 Module, ReLU, Max Pooling, Softmax |
|---|---|
| ID | adv_inception_v3 |
| SHOW MORE |
Inception v3 is a convolutional neural network architecture from the Inception family that makes several improvements including using Label Smoothing, Factorized 7 x 7 convolutions, and the use of an auxiliary classifer to propagate label information lower down the network (along with the use of batch normalization for layers in the sidehead). The key building block is an Inception Module.
This particular model was trained for study of adversarial examples (adversarial training).
To load a pretrained model:
import timm
m = timm.create_model('adv_inception_v3', pretrained=True)
m.eval()
Replace the model name with the variant you want to use, e.g. adv_inception_v3. You can find the IDs in the model summaries at the top of this page.
You can follow the timm recipe scripts for training a new model afresh.
@article{DBLP:journals/corr/abs-1804-00097,
author = {Alexey Kurakin and
Ian J. Goodfellow and
Samy Bengio and
Yinpeng Dong and
Fangzhou Liao and
Ming Liang and
Tianyu Pang and
Jun Zhu and
Xiaolin Hu and
Cihang Xie and
Jianyu Wang and
Zhishuai Zhang and
Zhou Ren and
Alan L. Yuille and
Sangxia Huang and
Yao Zhao and
Yuzhe Zhao and
Zhonglin Han and
Junjiajia Long and
Yerkebulan Berdibekov and
Takuya Akiba and
Seiya Tokui and
Motoki Abe},
title = {Adversarial Attacks and Defences Competition},
journal = {CoRR},
volume = {abs/1804.00097},
year = {2018},
url = {http://arxiv.org/abs/1804.00097},
archivePrefix = {arXiv},
eprint = {1804.00097},
timestamp = {Thu, 31 Oct 2019 16:31:22 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-00097.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
Image Classification
| BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
|---|---|---|---|---|
| ImageNet | adv_inception_v3 | Top 1 Accuracy | 77.58% | # 179 |
| Top 5 Accuracy | 93.74% | # 179 |
