Update index.html

cxrl2024/index.html

@@ -191,19 +191,11 @@ <h3 class="title is-3 has-text-centered">Method</h3>
         <br>
         <h4 class="title is-4 has-text-centered">Pipeline</h4>
         <div class="content has-text-justified">
-          <img src="./static/images/mainfigure.png" alt="Main figure">
+          <img src="./static/images/overview.png" alt="Main figure">
           <br>
           <p>
-            The pipeline of <i>EAGLE</i>. 
-            Leveraging the Laplacian matrix, which integrates hierarchically projected image key features and color 
-            affinity, the model exploits eigenvector clustering to capture object-level perspective cues defined 
-            as \( \mathrm{\mathcal{M}}_{eicue} \) and \( \mathrm{\tilde{\mathcal{M}}_{eicue}} \). 
-            Distilling knowledge from \( \mathrm{\mathcal{M}}_{eicue} \), our model further adopts an 
-            object-centric contrastive loss, utilizing the projected vector \( \mathrm{Z} \) and \( \mathrm{\tilde{Z}} \). 
-            The learnable prototype \( \mathrm{\Phi} \) assigned from \( \mathrm{Z} \) and \( \mathrm{\tilde{Z}} \), 
-            acts as a singular anchor that contrasts positive objects and negative objects. Our object-centric 
-            contrastive loss is computed in two distinct manners: intra(\( \mathrm{\mathcal{L}}_{obj} \))- and 
-            inter(\( \mathrm{\mathcal{L}}_{sc} \))-image to ensure semantic consistency.
+            The pipeline of <i>CXRL</i>. 
+            Our model employs policy gradient optimization utilizing multi-reward feedbacks, fine-tuning image generator and ACE to produce realistic and accurate CXR that corresponds closely to the input report.
           </p>
         </div>