Model Weight Released

README.md

@@ -10,6 +10,9 @@ International Conference on Learning Representations (ICLR) 2023\
 
 
 ## Updates
+***3/9/2023***\
+RevCol Detection & Segmentation model weights released.
+
 ***2/10/2023***\
 RevCol model weights released.
 
@@ -26,16 +29,12 @@ Initial commits: codes for ImageNet-1k and ImageNet-22k classification are relea
 - [x] ImageNet-1K and 22k Training Code  
 - [x] ImageNet-1K and 22k Model Weights
 - [x] Cascade Mask R-CNN COCO Object Detection Code & Model Weights
-- [ ] ADE20k Semantic Segmentation Code & Model Weights
+- [x] ADE20k Semantic Segmentation Code & Model Weights
 
 
 ## Introduction
 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.
 
-<p align="center">
-<img src="https://huggingface.co/LarryTsai/RevCol/blob/main/figures/title.png" width=100% height=100% 
-class="center">
-</p>
 
 ## Main Results on ImageNet with Pre-trained Models