Update index.html

index.html

@@ -205,11 +205,11 @@ <h2 class="title is-3">Using MAIA to remove spurious features</h2>
     <div class="hero-body">
       <h2 class="title is-3">Using MAIA to reveal biases</h2>
       <div class="content" style="text-align: left;">
-        <p>MAIA can also be applied to surface model-level biases. In a preliminary demonstration, we investigate biases in the outputs of an image classifier (ResNet-152) trained on a supervised ImageNet classification task. MAIA is easily adapted to this task by instrumenting an output logit corresponding to a particular image class as the system to be interpreted, and instructing MAIA to determine whether the actual distribution of images that receive high class scores matches the class label (see papaer Appendix for full MAIA instructions).</p>
+        <p>MAIA can also be applied to surface model-level biases. In a preliminary demonstration, we investigate biases in the outputs of an image classifier (ResNet-152) trained on a supervised ImageNet classification task. MAIA is easily adapted to this task by instrumenting an output logit corresponding to a particular image class as the system to be interpreted, and instructing MAIA to determine whether the actual distribution of images that receive high class scores matches the class label (see paper Appendix for full MAIA instructions).</p>
       </div>
       <figure style="display: flex; flex-direction: column; align-items: center; width: 100%;">
         <img src="./static/figures/bias_categories.png" style="width: 95%; height: auto;" alt="Bias Categories" />
-        <figcaption style="text-align: center;">Caption for the image goes here</figcaption>
+        <figcaption style="text-align: center;"><b>MAIA bias detection.</b> MAIA generates synthetic inputs to surface biases in ResNet-152 output classes. In some cases, MAIA discovers uniform behavior over the inputs (e.g. flagpole).</figcaption>
       </figure>
     </div>
     <hr>