Bill Psomas
first model commit
29f76b0
---
license: cc-by-4.0
datasets:
- imagenet-1k
metrics:
- accuracy
pipeline_tag: image-classification
language:
- en
tags:
- convnext
- convolutional neural network
- simpool
- dino
- computer vision
- deep learning
---
# Self-supervised ConvNeXt-S model
[ConvNeXt-S](https://arxiv.org/abs/2201.03545) official model trained on ImageNet-1k for 100 epochs. Self-supervision with [DINO](https://arxiv.org/abs/2104.14294). Reproduced for ICCV 2023 [SimPool](https://arxiv.org/abs/2309.06891) paper.
SimPool is a simple attention-based pooling method at the end of network, released in this [repository](https://github.com/billpsomas/simpool/).
Disclaimer: This model card is written by the author of SimPool, i.e. [Bill Psomas](http://users.ntua.gr/psomasbill/).
## Evaluation with k-NN
| k | top1 | top5 |
| ------- | ------- | ------- |
| 10 | 59.342 | 80.058 |
| 20 | 59.224 | 82.252 |
| 100 | 56.468 | 83.256 |
| 200 | 54.878 | 82.754 |
## BibTeX entry and citation info
```
@misc{psomas2023simpool,
title={Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?},
author={Bill Psomas and Ioannis Kakogeorgiou and Konstantinos Karantzalos and Yannis Avrithis},
year={2023},
eprint={2309.06891},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
```
@inproceedings{liu2022convnet,
title={A convnet for the 2020s},
author={Liu, Zhuang and Mao, Hanzi and Wu, Chao-Yuan and Feichtenhofer, Christoph and Darrell, Trevor and Xie, Saining},
booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
pages={11976--11986},
year={2022}
}
```
```
@inproceedings{caron2021emerging,
title={Emerging properties in self-supervised vision transformers},
author={Caron, Mathilde and Touvron, Hugo and Misra, Ishan and J{\'e}gou, Herv{\'e} and Mairal, Julien and Bojanowski, Piotr and Joulin, Armand},
booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
pages={9650--9660},
year={2021}
}
```