Update README.md

README.md

@@ -9,13 +9,11 @@ pinned: false
 
 | DINO | Dog |
 | :--: | :--: |
-| ![](https://i.imgur.com/kAShjbs.gif) | ![](https://i.imgur.com/xrMkCbg.gif) |
-
-
-[![TensorFlow 2.8](https://img.shields.io/badge/TensorFlow-2.8-FF6F00?logo=tensorflow)](https://github.com/tensorflow/tensorflow/releases/tag/v2.8.0)
+| ![dino](https://i.imgur.com/kAShjbs.gif) | ![dog](https://i.imgur.com/xrMkCbg.gif) |
 
 _By [Aritra Roy Gosthipaty](https://github.com/ariG23498) and [Sayak Paul](https://github.com/sayakpaul) (equal contribution)_
 
+<br>
 We probe into the representations learned by different families of Vision Transformers (supervised pre-training with ImageNet-21k, ImageNet-1k, distillation, self-supervised pre-training):
 
 * Original ViT [1] 
@@ -24,76 +22,7 @@ We probe into the representations learned by different families of Vision Transf
 
 We hope these tools will prove to be useful for the community. Please follow along with [this post on keras.io](https://keras.io/examples/vision/probing_vits/) for a better navigation through the repository. 
 
-
-## Self-attention visualization
-
-| Original Image | Attention Maps | Attention Maps Overlayed |
-| :--: | :--: | :--: |
-| ![original image](./assets/bird.png) | ![attention maps](./assets/dino_attention_heads_inferno.png) | ![attention maps overlay](./assets/dino_attention_heads.png) |
-
-https://user-images.githubusercontent.com/36856589/162609884-8e51156e-d461-421d-9f8a-4d4e48967bd6.mp4
-
-<small><a href=https://www.pexels.com/video/a-computer-generated-walking-dinosaur-4096297/>Original Video Source</a></small>
-
-https://user-images.githubusercontent.com/36856589/162609907-4e432dc4-a731-40f4-9a20-94e0c8f648bc.mp4
-
-<small><a href=https://www.pexels.com/video/a-dog-running-in-a-grass-field-4166343/>Original Video Source</a></small>
-
-## Supervised salient representations
-
-In the [DINO](https://ai.facebook.com/blog/dino-paws-computer-vision-with-self-supervised-transformers-and-10x-more-efficient-training/) blog post, the authors show a video with the following caption:
-
-> The original video is shown on the left. In the middle is a segmentation example generated by a supervised model, and on the right is one generated by DINO. 
-
-A screenshot of the video is as follows:
-
-<img width="764" alt="image" src="https://user-images.githubusercontent.com/36856589/162615199-b5133e51-460e-4864-a83e-5b8007339ff7.png"><br>
-
-
-We obtain the attention maps generated with the supervised pre-trained model and find that they are not that salient w.r.t the DINO model. We observe a similar behaviour in our experiments as well. The figure below shows the attention heatmaps extracted with
-a ViT-B16 model pre-trained (supervised) using ImageNet-1k:
-
-| Dinosaur | Dog | 
-| :--: | :--: | 
-| ![](./assets/supervised-dino.gif) | ![](./assets/supervised-dog.gif) | 
-
-We used this [Colab Notebook](https://github.com/sayakpaul/probing-vits/blob/main/notebooks/vitb16-attention-maps-video.ipynb) to conduct this experiment.
-
-## Hugging Face Spaces
-
-You can now probe into the ViTs with your own input images.
-
-| Attention Heat Maps | Attention Rollout |
-| :--: | :--: |
-| [![Generic badge](https://img.shields.io/badge/🤗%20Spaces-Attention%20Heat%20Maps-black.svg)](https://huggingface.co/spaces/probing-vits/attention-heat-maps) | [![Generic badge](https://img.shields.io/badge/🤗%20Spaces-Attention%20Rollout-black.svg)](https://huggingface.co/spaces/probing-vits/attention-rollout) |
-
-## Visualizing mean attention distances
-
-<div align="center">
-<img src="./assets/vit_base_i21k_patch16_224.png" width=450/>
-</div>
-
-## Methods
-
-**We don't propose any novel methods of probing the representations of neural networks. Instead we take the existing works and implement them in TensorFlow.**
-
-* Mean attention distance [1, 4]
-* Attention Rollout [5]
-* Visualization of the learned projection filters [1]
-* Visualization of the learned positioanl embeddings
-* Attention maps from individual attention heads [3]
-* Generation of attention heatmaps from videos [3]
-
-Another interesting repository that also visualizes ViTs in PyTorch: https://github.com/jacobgil/vit-explain.
-
-
-## Notes
-
-We first implemented the above-mentioned architectures in TensorFlow and then we populated the pre-trained parameters into them using the official codebases. In order to validate this, we evaluated the implementations on the ImageNet-1k validation set and ensured that the reported top-1 accuracies matched. 
-
-We value the spirit of open-source. So, if you spot any bugs in the code or see a scope for improvement don't hesitate to open up an issue or contribute a PR. We'd very much appreciate it. 
-
-
+<br>
 ## References
 
 [1] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale:  [https://arxiv.org/abs/2010.11929](https://arxiv.org/abs/2010.11929)
@@ -102,10 +31,7 @@ We value the spirit of open-source. So, if you spot any bugs in the code or see
 
 [3] DINO: https://arxiv.org/abs/2104.14294
 
-[4] Do Vision Transformers See Like Convolutional Neural Networks?:  [https://arxiv.org/abs/2108.08810](https://arxiv.org/abs/2108.08810)
-
-[5] [Quantifying Attention Flow in Transformers](https://arxiv.org/abs/2005.00928)
-
+<br>
 ## Acknowledgements
 
 - [PyImageSearch](https://pyimagesearch.com)