Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Retinaface
|
2 |
|
3 |
## Model Details
|
@@ -22,12 +29,30 @@ This model is intended for use in applications requiring face detection, such as
|
|
22 |
- Image processing pipelines
|
23 |
- Photo management applications
|
24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
## Citation
|
26 |
-
|
|
|
|
|
|
|
27 |
title={RetinaFace: Single-stage Dense Face Localisation in the Wild},
|
28 |
author={Jiankang Deng and Jia Guo and Yuxiang Zhou and Jinke Yu and Irene Kotsia and Stefanos Zafeiriou},
|
29 |
year={2019},
|
30 |
eprint={1905.00641},
|
31 |
archivePrefix={arXiv},
|
32 |
primaryClass={cs.CV},
|
33 |
-
url={https://arxiv.org/abs/1905.00641
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- model_hub_mixin
|
4 |
+
- pytorch_model_hub_mixin
|
5 |
+
|
6 |
+
---
|
7 |
+
|
8 |
# Retinaface
|
9 |
|
10 |
## Model Details
|
|
|
29 |
- Image processing pipelines
|
30 |
- Photo management applications
|
31 |
|
32 |
+
## Evaluation Results
|
33 |
+
The model was evaluated on the WIDER FACE dataset
|
34 |
+
|
35 |
+
## Limitations and Biases
|
36 |
+
While the Retinaface model performs well in many conditions, it may have limitations, including:
|
37 |
+
|
38 |
+
Reduced accuracy in detecting faces with heavy occlusions
|
39 |
+
Potential biases towards the demographic distribution of the training dataset
|
40 |
+
Ethical Considerations
|
41 |
+
When using face detection technologies, it is essential to consider the ethical implications, such as privacy concerns and potential biases. Ensure that the use of this model complies with relevant regulations and guidelines.
|
42 |
+
|
43 |
## Citation
|
44 |
+
If you use the Retinaface model in your research or application, please cite the following paper:
|
45 |
+
|
46 |
+
bibtex
|
47 |
+
@misc{deng2019retinafacesinglestagedenseface,
|
48 |
title={RetinaFace: Single-stage Dense Face Localisation in the Wild},
|
49 |
author={Jiankang Deng and Jia Guo and Yuxiang Zhou and Jinke Yu and Irene Kotsia and Stefanos Zafeiriou},
|
50 |
year={2019},
|
51 |
eprint={1905.00641},
|
52 |
archivePrefix={arXiv},
|
53 |
primaryClass={cs.CV},
|
54 |
+
url={https://arxiv.org/abs/1905.00641}
|
55 |
+
}
|
56 |
+
|
57 |
+
## Acknowledgements
|
58 |
+
We thank the contributors and the open-source community for their valuable support in developing this model. Special thanks to the authors of the original Retinaface paper and the WIDER FACE dataset.
|