| | --- |
| | license: cc-by-4.0 |
| | datasets: |
| | - imagenet-1k |
| | metrics: |
| | - accuracy |
| | pipeline_tag: image-classification |
| | language: |
| | - en |
| | tags: |
| | - resnet |
| | - convolutional neural network |
| | - simpool |
| | - computer vision |
| | - deep learning |
| | --- |
| | |
| | # Supervised ResNet-50 model |
| |
|
| | ResNet-50 official model trained on ImageNet-1k for 100 epochs. 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/). |
| |
|
| | ## 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} |
| | } |
| | ``` |
