readme update

README.md

@@ -10,6 +10,18 @@
 ## Abstract
 Vision transformers (ViTs) are top-performing models on many computer vision benchmarks and can accurately predict human behavior on object recognition tasks. However, researchers question the value of using ViTs as models of biological learning because ViTs are thought to be more “data hungry” than brains, with ViTs requiring more training data to reach similar levels of performance. To test this assumption, we directly compared the learning abilities of ViTs and animals, by performing parallel controlled-rearing experiments on ViTs and newborn chicks. We first raised chicks in impoverished visual environments containing a single object, then simulated the training data available in those environments by building virtual animal chambers in a video game engine. We recorded the first-person images acquired by agents moving through the virtual chambers and used those images to train self-supervised ViTs that leverage time as a teaching signal, akin to biological visual systems. When ViTs were trained “through the eyes” of newborn chicks, the ViTs solved the same view-invariant object recognition tasks as the chicks. Thus, ViTs were not more data hungry than newborn visual systems: both learned view-invariant object representations in impoverished visual environments. The flexible and generic attention-based learning mechanism in ViTs—combined with the embodied data streams available to newborn animals—appears sufficient to drive the development of animal-like object recognition.
 
+## About ViT-CoT
+
+<h3>Encoder (ViT):</h3><p>The image is first divided into smaller 8x8 patches and then reshaped into a sequence of flattened patches. A learnable positional embedding is added to each flattened patch, and a class token (CLS_Token) is added to the sequence. The resulting embedding is then sequentially processed by transformer blocks while also being analyzed in parallel by attention heads, which generate attention filters shown next to each head. The learned representation of the image is adjusted based on a contrastive learning through time loss function.</p>
+
+<img src="./media/encoder.png" style="height:300px">
+
+<h3>Contrastive Learning Through Time Loss Function (CoT):</h3><p>
+ViT-CoT leverages the temporal structure of embodied data streams. Learning occurs by making successive views (images seen in a 300 ms temporal window) more similar in the embedding space.
+</p>
+
+<img src="./media/loss.png" style="height:300px">
+
 ## Code Base Organization
 ```
 ViT-CoT