| Training Techniques | SGD with Momentum, Weight Decay |
|---|---|
| Architecture | 1x1 Convolution, Batch Normalization, Convolution, Grouped Convolution, Global Average Pooling, ResNeXt Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | ssl_resnext101_32x16d |
| SHOW MORE |
| Training Techniques | SGD with Momentum, Weight Decay |
|---|---|
| Architecture | 1x1 Convolution, Batch Normalization, Convolution, Grouped Convolution, Global Average Pooling, ResNeXt Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | ssl_resnext101_32x4d |
| SHOW MORE |
| Training Techniques | SGD with Momentum, Weight Decay |
|---|---|
| Architecture | 1x1 Convolution, Batch Normalization, Convolution, Grouped Convolution, Global Average Pooling, ResNeXt Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | ssl_resnext101_32x8d |
| SHOW MORE |
| Training Techniques | SGD with Momentum, Weight Decay |
|---|---|
| Architecture | 1x1 Convolution, Batch Normalization, Convolution, Grouped Convolution, Global Average Pooling, ResNeXt Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | ssl_resnext50_32x4d |
| SHOW MORE |
A ResNeXt repeats a building block that aggregates a set of transformations with the same topology. Compared to a ResNet, it exposes a new dimension, cardinality (the size of the set of transformations) $C$, as an essential factor in addition to the dimensions of depth and width.
The model in this collection utilises semi-supervised learning to improve the performance of the model. The approach brings important gains to standard architectures for image, video and fine-grained classification.
Please note the CC-BY-NC 4.0 license on theses weights, non-commercial use only.
To load a pretrained model:
import timm
m = timm.create_model('ssl_resnext50_32x4d', pretrained=True)
m.eval()
Replace the model name with the variant you want to use, e.g. ssl_resnext50_32x4d. 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-1905-00546,
author = {I. Zeki Yalniz and
Herv{\'{e}} J{\'{e}}gou and
Kan Chen and
Manohar Paluri and
Dhruv Mahajan},
title = {Billion-scale semi-supervised learning for image classification},
journal = {CoRR},
volume = {abs/1905.00546},
year = {2019},
url = {http://arxiv.org/abs/1905.00546},
archivePrefix = {arXiv},
eprint = {1905.00546},
timestamp = {Mon, 28 Sep 2020 08:19:37 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-00546.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
Image Classification on ImageNet
| MODEL | TOP 1 ACCURACY | TOP 5 ACCURACY |
|---|---|---|
| ssl_resnext101_32x16d | 81.84% | 96.09% |
| ssl_resnext101_32x8d | 81.61% | 96.04% |
| ssl_resnext101_32x4d | 80.91% | 95.73% |
| ssl_resnext50_32x4d | 80.3% | 95.41% |
