Commit
•
98c8cfb
1
Parent(s):
cdc7e13
Update README.md
Browse files
README.md
CHANGED
@@ -100,7 +100,7 @@ for ["TransNeXt: Robust Foveal Visual Perception for Vision Transformers"](https
|
|
100 |
| Backbone | Pretrained Model| Crop Size |Lr Schd| mIoU|mIoU (ms+flip)| #Params | Download |Config| Log |
|
101 |
|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|
102 |
| TransNeXt-Tiny | [ImageNet-1K](https://huggingface.co/DaiShiResearch/transnext-tiny-224-1k/resolve/main/transnext_tiny_224_1k.pth?download=true)|512x512|160K|51.1|51.5/51.7|59M|[model](https://huggingface.co/DaiShiResearch/upernet-transnext-tiny-ade/resolve/main/upernet_transnext_tiny_512x512_160k_ade20k_in1k.pth?download=true)|[config](https://github.com/DaiShiResearch/TransNeXt/tree/main/segmentation/upernet/configs/upernet_transnext_tiny_512x512_160k_ade20k_ss.py)|[log](https://huggingface.co/DaiShiResearch/upernet-transnext-tiny-ade/blob/main/upernet_transnext_tiny_512x512_160k_ade20k_ss.log.json)|
|
103 |
-
| TransNeXt-Small | [ImageNet-1K](https://huggingface.co/DaiShiResearch/transnext-small-224-1k/resolve/main/transnext_small_224_1k.pth?download=true)|512x512|160K|52.2|52.5/
|
104 |
| TransNeXt-Base | [ImageNet-1K](https://huggingface.co/DaiShiResearch/transnext-base-224-1k/resolve/main/transnext_base_224_1k.pth?download=true)|512x512|160K|53.0|53.5/53.7|121M|[model](https://huggingface.co/DaiShiResearch/upernet-transnext-base-ade/resolve/main/upernet_transnext_base_512x512_160k_ade20k_in1k.pth?download=true)|[config](https://github.com/DaiShiResearch/TransNeXt/tree/main/segmentation/upernet/configs/upernet_transnext_base_512x512_160k_ade20k_ss.py)|[log](https://huggingface.co/DaiShiResearch/upernet-transnext-base-ade/blob/main/upernet_transnext_base_512x512_160k_ade20k_ss.log.json)|
|
105 |
* In the context of multi-scale evaluation, TransNeXt reports test results under two distinct scenarios: **interpolation** and **extrapolation** of relative position bias.
|
106 |
|
@@ -117,11 +117,11 @@ for ["TransNeXt: Robust Foveal Visual Perception for Vision Transformers"](https
|
|
117 |
If you find our work helpful, please consider citing the following bibtex. We would greatly appreciate a star for this
|
118 |
project.
|
119 |
|
120 |
-
@
|
121 |
-
author
|
122 |
-
title
|
123 |
-
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
}
|
|
|
100 |
| Backbone | Pretrained Model| Crop Size |Lr Schd| mIoU|mIoU (ms+flip)| #Params | Download |Config| Log |
|
101 |
|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|
102 |
| TransNeXt-Tiny | [ImageNet-1K](https://huggingface.co/DaiShiResearch/transnext-tiny-224-1k/resolve/main/transnext_tiny_224_1k.pth?download=true)|512x512|160K|51.1|51.5/51.7|59M|[model](https://huggingface.co/DaiShiResearch/upernet-transnext-tiny-ade/resolve/main/upernet_transnext_tiny_512x512_160k_ade20k_in1k.pth?download=true)|[config](https://github.com/DaiShiResearch/TransNeXt/tree/main/segmentation/upernet/configs/upernet_transnext_tiny_512x512_160k_ade20k_ss.py)|[log](https://huggingface.co/DaiShiResearch/upernet-transnext-tiny-ade/blob/main/upernet_transnext_tiny_512x512_160k_ade20k_ss.log.json)|
|
103 |
+
| TransNeXt-Small | [ImageNet-1K](https://huggingface.co/DaiShiResearch/transnext-small-224-1k/resolve/main/transnext_small_224_1k.pth?download=true)|512x512|160K|52.2|52.5/52.8|80M|[model](https://huggingface.co/DaiShiResearch/upernet-transnext-small-ade/resolve/main/upernet_transnext_small_512x512_160k_ade20k_in1k.pth?download=true)|[config](https://github.com/DaiShiResearch/TransNeXt/tree/main/segmentation/upernet/configs/upernet_transnext_small_512x512_160k_ade20k_ss.py)|[log](https://huggingface.co/DaiShiResearch/upernet-transnext-small-ade/blob/main/upernet_transnext_small_512x512_160k_ade20k_ss.log.json)|
|
104 |
| TransNeXt-Base | [ImageNet-1K](https://huggingface.co/DaiShiResearch/transnext-base-224-1k/resolve/main/transnext_base_224_1k.pth?download=true)|512x512|160K|53.0|53.5/53.7|121M|[model](https://huggingface.co/DaiShiResearch/upernet-transnext-base-ade/resolve/main/upernet_transnext_base_512x512_160k_ade20k_in1k.pth?download=true)|[config](https://github.com/DaiShiResearch/TransNeXt/tree/main/segmentation/upernet/configs/upernet_transnext_base_512x512_160k_ade20k_ss.py)|[log](https://huggingface.co/DaiShiResearch/upernet-transnext-base-ade/blob/main/upernet_transnext_base_512x512_160k_ade20k_ss.log.json)|
|
105 |
* In the context of multi-scale evaluation, TransNeXt reports test results under two distinct scenarios: **interpolation** and **extrapolation** of relative position bias.
|
106 |
|
|
|
117 |
If you find our work helpful, please consider citing the following bibtex. We would greatly appreciate a star for this
|
118 |
project.
|
119 |
|
120 |
+
@InProceedings{shi2023transnext,
|
121 |
+
author = {Dai Shi},
|
122 |
+
title = {TransNeXt: Robust Foveal Visual Perception for Vision Transformers},
|
123 |
+
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
|
124 |
+
month = {June},
|
125 |
+
year = {2024},
|
126 |
+
pages = {17773-17783}
|
127 |
}
|