Initial commit

index.html

@@ -91,18 +91,30 @@ <h2>Abstract</h2>
 </section>
 <br>
 
+
+<style>
+ .image {
+ width: 100%;
+ }
+
+ @media (min-width: 1200px) {
+ .image {
+ width: 80%;
+ }
+ }
+</style>
 <section>
  <div class="container">
  <div class="row">
  <div class="col-12 text-center">
- <h2>Preliminaries</h2>
+ <h2>Preliminary</h2>
  <!-- <hr style="margin-top:0px"> -->
  </div>
  <br>
  <div class="col-12">
  <p class="text-left">
  <center>
- <img src="images/preliminary.png" style="width:75%; margin-bottom:20px;">
+ <img src="images/preliminary.png" class="image" style="margin-top:10px; margin-bottom:20px;">
  </center>
  <!-- <h4>Mean-Shift</h4> -->
  <!-- We revisit the mean-shift and introduce contrastive mean-shift (CMS) learning for generalized category discovery. -->
@@ -143,7 +155,7 @@ <h4>Learning framework: Contrastive Mean-Shift learning (CMS)</h4>
  <br>
  <h4>Validation: Estimating the number of clusters</h4>
  <center>
- <img src="images/validation.png" style="width:80%; margin-top:10px; margin-bottom:20px;">
+ <img src="images/validation.png" class="image" style="margin-top:10px; margin-bottom:20px;">
  </center>
  During training, we estimate the number of clusters K at the end of every epoch for a fairer and efficient validation. We apply 
  agglomerative clustering on the validation set to obtain clustering results for different number of clusters. Among them, the 
@@ -154,7 +166,7 @@ <h4>Validation: Estimating the number of clusters</h4>
  <br>
  <h4>Inference: Iterative Mean-Shift (IMS)</h4>
  <center>
- <img src="images/inference.png" style="width:80%; margin-top:10px; margin-bottom:20px;">
+ <img src="images/inference.png" class="image" style="margin-top:10px; margin-bottom:20px;">
  </center>
  To improve the final clustering property of the embeddings, we perform multi-step mean shift on the embeddings before
  agglomerative clustering. Starting from the initial embeddings from the learned encoder, we update them to $t$-step