Update README.md

README.md

@@ -1,3 +1,6 @@
+---
+license: apache-2.0
+---
 # Reversible Column Networks 
 This repo is the official implementation of:
 
@@ -10,8 +13,11 @@ International Conference on Learning Representations (ICLR) 2023\
 
 
 ## Updates
-***3/9/2023***\
-RevCol Detection & Segmentation model weights released.
+**3/15/2023***\
+RevCol Huge checkpoint for segmentation released! Add visualization tools.
+
+**3/9/2023***\
+Detection, Segmentation Code and Model Weights Released.
 
 ***2/10/2023***\
 RevCol model weights released.
@@ -36,6 +42,7 @@ Initial commits: codes for ImageNet-1k and ImageNet-22k classification are relea
 RevCol is composed of multiple copies of subnetworks, named columns respectively, between which multi-level reversible connections are employed. RevCol coud serves as a foundation model backbone for various tasks in computer vision including classification, detection and segmentation.
 
 
+
 ## Main Results on ImageNet with Pre-trained Models
 
 | name | pretrain | resolution | #params |FLOPs | acc@1 | pretrained model | finetuned model |
@@ -47,7 +54,9 @@ RevCol is composed of multiple copies of subnetworks, named columns respectively
 | RevCol-B<sup>\*</sup> | ImageNet-22K | 384x384 | 138M | 48.9G | 86.7 |[baidu](https://pan.baidu.com/s/1l8zOFifgC8fZtBpHK2ZQHg?pwd=rh58)/[github](https://github.com/megvii-research/RevCol/releases/download/checkpoint/revcol_base_22k.pth)| [baidu](https://pan.baidu.com/s/18G0zAUygKgu58s2AjCBpsw?pwd=rv86)/[github](https://github.com/megvii-research/RevCol/releases/download/checkpoint/revcol_base_22k_1kft_384.pth)|
 | RevCol-L<sup>\*</sup> | ImageNet-22K | 224x224 | 273M | 39G | 86.6 |[baidu](https://pan.baidu.com/s/1ueKqh3lFAAgC-vVU34ChYA?pwd=qv5m)/[github](https://github.com/megvii-research/RevCol/releases/download/checkpoint/revcol_large_22k.pth)| [baidu](https://pan.baidu.com/s/1CsWmcPcwieMzXE8pVmHh7w?pwd=qd9n)/[github](https://github.com/megvii-research/RevCol/releases/download/checkpoint/revcol_large_22k_1kft_224.pth)|
 | RevCol-L<sup>\*</sup> | ImageNet-22K | 384x384 | 273M | 116G | 87.6 |[baidu](https://pan.baidu.com/s/1ueKqh3lFAAgC-vVU34ChYA?pwd=qv5m)/[github](https://github.com/megvii-research/RevCol/releases/download/checkpoint/revcol_large_22k.pth)| [baidu](https://pan.baidu.com/s/1VmCE3W3Xw6-Lo4rWrj9Xzg?pwd=x69r)/[github](https://github.com/megvii-research/RevCol/releases/download/checkpoint/revcol_large_22k_1kft_384.pth)|
+| RevCol-H<sup>\*+</sup>  | Megdata-168M | pretrain 224 / finetune 640 | 2.1B | 2537 | 90.0 |[huggingface](https://huggingface.co/LarryTsai/RevCol/blob/main/revcol_models/classification/revcol_huge_megdata.pth)|[huggingface](https://huggingface.co/LarryTsai/RevCol/blob/main/revcol_models/classification/revcol_huge_megdata_in1k.pth)|
 
+[+]: Note that we use a slightly different model on RevCol-H with one more branch from the bottom level to the top one. Later experiments prove that this connection is unnecessary, however, consider RevCol-H's training cost, we do not retrain it.
 ## Getting Started
 Please refer to [INSTRUCTIONS.md](INSTRUCTIONS.md) for setting up, training and evaluation details.
 
@@ -75,4 +84,4 @@ If you have any questions about this repo or the original paper, please contact
   year={2023},
   url={https://openreview.net/forum?id=Oc2vlWU0jFY}
 }
-```
+```