Update README
Browse files
README.md
CHANGED
@@ -69,7 +69,7 @@ At inference time, images are resized/rescaled to the same resolution (256x256),
|
|
69 |
|
70 |
### Pretraining
|
71 |
|
72 |
-
The model was trained on a single 8-GPU node for 3 days. Training resolution is 224.
|
73 |
|
74 |
## Evaluation results
|
75 |
|
@@ -80,22 +80,22 @@ Note that for fine-tuning, the best results are obtained with a higher resolutio
|
|
80 |
### BibTeX entry and citation info
|
81 |
|
82 |
```bibtex
|
83 |
-
@misc{
|
84 |
-
title={
|
85 |
-
author={
|
86 |
-
year={
|
87 |
-
eprint={
|
88 |
archivePrefix={arXiv},
|
89 |
primaryClass={cs.CV}
|
90 |
}
|
91 |
```
|
92 |
|
93 |
```bibtex
|
94 |
-
@misc{
|
95 |
-
title={
|
96 |
-
author={
|
97 |
-
year={
|
98 |
-
eprint={
|
99 |
archivePrefix={arXiv},
|
100 |
primaryClass={cs.CV}
|
101 |
}
|
|
|
69 |
|
70 |
### Pretraining
|
71 |
|
72 |
+
The model was trained on a single 8-GPU node for 3 days. Training resolution is 224. For all hyperparameters (such as batch size and learning rate) we refer to table 9 of the original paper.
|
73 |
|
74 |
## Evaluation results
|
75 |
|
|
|
80 |
### BibTeX entry and citation info
|
81 |
|
82 |
```bibtex
|
83 |
+
@misc{touvron2021training,
|
84 |
+
title={Training data-efficient image transformers & distillation through attention},
|
85 |
+
author={Hugo Touvron and Matthieu Cord and Matthijs Douze and Francisco Massa and Alexandre Sablayrolles and Hervé Jégou},
|
86 |
+
year={2021},
|
87 |
+
eprint={2012.12877},
|
88 |
archivePrefix={arXiv},
|
89 |
primaryClass={cs.CV}
|
90 |
}
|
91 |
```
|
92 |
|
93 |
```bibtex
|
94 |
+
@misc{wu2020visual,
|
95 |
+
title={Visual Transformers: Token-based Image Representation and Processing for Computer Vision},
|
96 |
+
author={Bichen Wu and Chenfeng Xu and Xiaoliang Dai and Alvin Wan and Peizhao Zhang and Zhicheng Yan and Masayoshi Tomizuka and Joseph Gonzalez and Kurt Keutzer and Peter Vajda},
|
97 |
+
year={2020},
|
98 |
+
eprint={2006.03677},
|
99 |
archivePrefix={arXiv},
|
100 |
primaryClass={cs.CV}
|
101 |
}
|