Update README.md

README.md

@@ -49,12 +49,12 @@ with torch.inference_mode():
     outputs = model(**inputs)
 
 # Prepare the original image size in the format (height, width)
-original_image_sizes = [(image.height, image.width)]
+target_sizes = [(image.height, image.width)]
 
 # Post-process the model outputs to get final segmentation prediction
 preds = processor.post_process_instance_segmentation(
     outputs,
-    original_image_sizes=original_image_sizes,
+    target_sizes=target_sizes,
 )
 
 # Visualize the segmentation mask
@@ -62,4 +62,15 @@ plt.imshow(preds[0]["segmentation"])
 plt.axis("off")
 plt.title("Instance Segmentation")
 plt.show()
-```
+```
+
+## Citation
+If you find our work useful, please consider citing us as:
+```bibtex
+@inproceedings{kerssies2025eomt,
+  author    = {Kerssies, Tommie and Cavagnero, Niccolò and Hermans, Alexander and Norouzi, Narges and Averta, Giuseppe and Leibe, Bastian and Dubbelman, Gijs and de Geus, Daan},
+  title     = {Your ViT is Secretly an Image Segmentation Model},
+  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year      = {2025},
+}
+```