Update README.md

README.md

@@ -3,6 +3,7 @@
 This is a PyTorch implementation for [Graphical Contrastive Losses for Scene Graph Generation, CVPR2019](https://arxiv.org/abs/1903.02728).
 
 ![alt text](https://github.com/NVIDIA/ContrastiveLosses4VRD/blob/master/Loss_illustration.PNG)
+Example results of RelDN with L0 only and with our losses. The top row shows RelDN outputs and the bottom row visualizes the learned predicate CNN features of the two models. Red and green boxes highlight the wrong and right outputs (the first row) or feature saliency (the second row).
 
 ## Cloning
 ```