introduction updates

introduction.md

@@ -9,7 +9,7 @@ is built upon the pre-trained [Italian BERT](https://huggingface.co/dbmdz/bert-b
 
 In building this project we kept in mind the following principles:
 
-+ **Novel Contributions**: We created a dataset of ~1.4 million Italian image-text pairs (**that we will share with the community**) and, to the best of our knowledge, we trained the best Italian CLIP model currently in existence;
++ **Novel Contributions**: We created an impressive dataset of ~1.4 million Italian image-text pairs (**that we will share with the community**) and, to the best of our knowledge, we trained the best Italian CLIP model currently in existence;
 + **Scientific Validity**: Claim are easy, facts are hard. That's why validation is important to assess the real impact of a model. We thoroughly evaluated our models on two tasks and made the validation reproducible for everybody.
 + **Broader Outlook**: We always kept in mind which are the possible usages and limitations of this model.
 
@@ -25,9 +25,18 @@ In this demo, we present two tasks:
 compute the similarity between this string of text with respect to a set of images. The webapp is going to display the images that
 have the highest similarity with the text query.
 
+<img src="https://huggingface.co/spaces/clip-italian/clip-italian-demo/raw/main/static/img/text_to_image.png" alt="drawing" width="95%"/>
+
 + *Image to Text*: This task is essentially a zero-shot image classification task. The user is asked for an image and for a set of captions/labels and CLIP
 is going to compute the similarity between the image and each label. The webapp is going to display a probability distribution over the captions.
 
+<img src="https://huggingface.co/spaces/clip-italian/clip-italian-demo/raw/main/static/img/image_to_text.png" alt="drawing" width="95%"/>
+
++ *Localization*: This is one of ours **very cool** features and at the best of our knowledge, it is a novel contribution. We can use CLIP
+to find where "something" (like a "cat") is an image. The location of the object is computed by masking different areas of the image and looking at how the similarity to the image description changes.
+
+<img src="https://huggingface.co/spaces/clip-italian/clip-italian-demo/raw/main/static/img/gatto_cane.png" alt="drawing" width="95%"/>
+
 + *Examples & Applications*: This page showcases some interesting results we got from the model, we believe that there are 
 different applications that can start from here.