metadata

license: apache-2.0
tags:
  - self-supervised learning
  - vision
  - GMML
inference: false

Model description

GMML is a self-supervised learning model that learns to group masked pixels in an image. The model is trained on ImageNet-1K.

Model Sources

https://github.com/Sara-Ahmed/GMML
https://arxiv.org/abs/2205.14986

Model Card Authors

Sara Atito, Muhammad Awais, Josef Kittler

How to use

from transformers import BertConfig, BertModel

config = BertConfig()
model = BertModel(config)

model.push_to_hub("nielsr/my-awesome-bert-model")

# reload
model = BertModel.from_pretrained("nielsr/my-awesome-bert-model")

BibTeX entry and citation info

@inproceedings{atito2023gmml,
  title={GMML is all you need},
  author={Atito, Sara and Awais, Muhammed and Nandam, Srinivasa and Kittler, Josef},
  booktitle={2023 IEEE International Conference on Image Processing (ICIP)},
  pages={2125--2129},
  year={2023},
  organization={IEEE}
}