Update README

README.md

@@ -10,7 +10,7 @@ library_name: transformers
 pipeline_tag: zero-shot-image-classification
 ---
 
-# TIPSv2 — G/14
+# TIPSv2 — g/14
 
 TIPSv2 (Text-Image Pre-training with Spatial awareness) is a family of contrastive vision-language models that produce spatially rich image features aligned with text embeddings. This is the Giant variant with 1.1B vision params and 389M text params.
 
@@ -74,6 +74,17 @@ similarity = cls @ text_emb.T
 prediction = similarity.argmax(dim=-1)
 ```
 
+### Zero-shot segmentation
+
+```python
+import numpy as np
+from sklearn.decomposition import PCA
+
+spatial = out.patch_tokens.reshape(1, 32, 32, 1536)
+feat = spatial[0].detach().numpy().reshape(-1, 1536)
+rgb = PCA(n_components=3).fit_transform(feat).reshape(32, 32, 3)
+```
+
 ### GPU inference
 
 ```python