Update README.md

README.md

@@ -25,7 +25,7 @@ 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
-- [ ] Cascade Mask R-CNN COCO Object Detection Code & Model Weights
+- [x] Cascade Mask R-CNN COCO Object Detection Code & Model Weights
 - [ ] ADE20k Semantic Segmentation Code & Model Weights
 
 
@@ -33,7 +33,7 @@ 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.
 
 <p align="center">
-<img src="figures/title.png" width=100% height=100% 
+<img src="https://huggingface.co/LarryTsai/RevCol/blob/main/figures/title.png" width=100% height=100% 
 class="center">
 </p>