Update README.md

README.md

@@ -101,21 +101,43 @@ outputs = model(pixel_values)
 
 ### Evaluation on Vision Capability
 
-We present a comprehensive evaluation of the vision encoder’s performance across various domains and tasks. The evaluation is divided into two key categories: (1) image classification, representing global-view semantic quality, and (2) semantic segmentation, capturing local-view semantic quality. This approach allows us to assess the representation quality of InternViT across its successive version updates. Please refer to our technical report for more details.
+We present a comprehensive evaluation of the vision encoder’s performance across various domains and tasks. 
+The evaluation is divided into two key categories:
 
-#### Image Classification
+(1) text retrial; 
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/0Zx1JWB-2kHEfLbboiVy1.png)
+(2) image segmentation;
 
-**Image classification performance across different versions of InternViT.** We use IN-1K for training and evaluate on the IN-1K validation set as well as multiple ImageNet variants, including IN-ReaL, IN-V2, IN-A, IN-R, and IN-Sketch. Results are reported for both linear probing and attention pooling probing methods, with average accuracy for each method. ∆ represents the performance gap between attention pooling probing and linear probing, where a larger ∆ suggests a shift from learning simple linear features to capturing more complex, nonlinear semantic representations.
+(3) visual question answering;
 
-#### Semantic Segmentation Performance
+This approach allows us to assess the representation quality of TokenOCR. 
+Please refer to our technical report for more details.
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/XjJx5WSIXjsaQGLPCsQuP.png)
+#### text retrial
 
-**Semantic segmentation performance across different versions of InternViT.** The models are evaluated on ADE20K and COCO-Stuff-164K using three configurations: linear probing, head tuning, and full tuning. The table shows the mIoU scores for each configuration and their averages. ∆1 represents the gap between head tuning and linear probing, while ∆2 shows the gap between full tuning and linear probing. A larger ∆ value indicates a shift from simple linear features to more complex, nonlinear representations.
+<div align="center">
+  <img width="500" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/650d4a36cbd0c7d550d3b41b/b2b2g23o9GMmPe1PiCn0f.png">
+</div>
+
+
+<!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/650d4a36cbd0c7d550d3b41b/b2b2g23o9GMmPe1PiCn0f.png) -->
+
+#### image segmentation
+
+<div align="center">
+  <img width="500" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/650d4a36cbd0c7d550d3b41b/C15-Ica6XVfX6y_MgiVds.png">
+</div>
+
+<!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/650d4a36cbd0c7d550d3b41b/C15-Ica6XVfX6y_MgiVds.png) -->
 
+#### visual question answering
+
+<div align="center">
+  <img width="500" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/650d4a36cbd0c7d550d3b41b/IbLZ0CxCxDkTaHAMe7M0Q.png">
+</div>
 
+<!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/650d4a36cbd0c7d550d3b41b/IbLZ0CxCxDkTaHAMe7M0Q.png)
+ -->
 ## TokenVL
 
 we employ the TokenOCR as the visual foundation model and further develop an MLLM, named TokenVL, tailored for document understanding.