diff --git a/index.html b/index.html
index 2f26971..b962e4b 100644
--- a/index.html
+++ b/index.html
@@ -81,8 +81,6 @@
ImagenHub: Standardizing the evaluatio
-
-
♠️University of Waterloo,
@@ -96,6 +94,7 @@ ImagenHub: Standardizing the evaluatio
@@ -208,11 +228,11 @@ Abstract
Overall Results
-
+
Figure 2: The best and the average model performance in each task.
-
+
Figure 3: Model performance and standard deviation in each task.
@@ -317,7 +337,7 @@
Comprehensive Results
Unknown |
0.67±0.06 |
0.92±0.06 |
-
0.73±0.07 |
+
0.73±0.07 |
0.34 |
- |
0.51 |
@@ -329,7 +349,7 @@
Comprehensive Results
Unknown |
0.65±0.02 |
0.62±0.06 |
-
0.59±0.02 |
+
0.59±0.02 |
0.32 |
- |
0.51 |
diff --git a/static/images/overall_results_v2.png b/static/images/overall_results_v2.png
new file mode 100644
index 0000000..b47f2be
Binary files /dev/null and b/static/images/overall_results_v2.png differ
diff --git a/static/images/task_performance_v2.png b/static/images/task_performance_v2.png
new file mode 100644
index 0000000..fea550e
Binary files /dev/null and b/static/images/task_performance_v2.png differ