Update README.md

README.md

@@ -113,99 +113,8 @@ S-measure (`S_α`), prompt-free, higher is better. Both columns come from one sc
 identical rows, so the difference isolates the weights — the SAM 3 numbers are a fresh rescore, not
 values copied from a paper. Changes below 0.002 `S_α` are treated as measurement noise.
 
-<table>
-  <thead>
-    <tr>
-      <th>Split</th>
-      <th style="text-align: right;">SAM 3</th>
-      <th style="text-align: right;">MultiMatte</th>
-      <th style="text-align: right;">Δ</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <td colspan="4"><strong>Dichotomous (DIS5K)</strong></td>
-    </tr>
-    <tr>
-      <td>DIS-VD</td>
-      <td style="text-align: right;">0.667</td>
-      <td style="text-align: right;"><strong>0.901</strong></td>
-      <td style="text-align: right;">+0.233</td>
-    </tr>
-    <tr>
-      <td>DIS-TE1</td>
-      <td style="text-align: right;">0.667</td>
-      <td style="text-align: right;"><strong>0.901</strong></td>
-      <td style="text-align: right;">+0.234</td>
-    </tr>
-    <tr>
-      <td>DIS-TE2</td>
-      <td style="text-align: right;">0.703</td>
-      <td style="text-align: right;"><strong>0.923</strong></td>
-      <td style="text-align: right;">+0.220</td>
-    </tr>
-    <tr>
-      <td>DIS-TE3</td>
-      <td style="text-align: right;">0.685</td>
-      <td style="text-align: right;"><strong>0.921</strong></td>
-      <td style="text-align: right;">+0.236</td>
-    </tr>
-    <tr>
-      <td>DIS-TE4</td>
-      <td style="text-align: right;">0.649</td>
-      <td style="text-align: right;"><strong>0.893</strong></td>
-      <td style="text-align: right;">+0.245</td>
-    </tr>
-    <tr>
-      <td colspan="4"><strong>Salient objects</strong></td>
-    </tr>
-    <tr>
-      <td>DAVIS-S †</td>
-      <td style="text-align: right;">0.913</td>
-      <td style="text-align: right;"><strong>0.979</strong></td>
-      <td style="text-align: right;">+0.066</td>
-    </tr>
-    <tr>
-      <td>HRSOD-TE</td>
-      <td style="text-align: right;">0.930</td>
-      <td style="text-align: right;"><strong>0.969</strong></td>
-      <td style="text-align: right;">+0.039</td>
-    </tr>
-    <tr>
-      <td>UHRSD-TE</td>
-      <td style="text-align: right;">0.877</td>
-      <td style="text-align: right;"><strong>0.961</strong></td>
-      <td style="text-align: right;">+0.084</td>
-    </tr>
-    <tr>
-      <td>DUTS-TE</td>
-      <td style="text-align: right;">0.892</td>
-      <td style="text-align: right;"><strong>0.954</strong></td>
-      <td style="text-align: right;">+0.062</td>
-    </tr>
-    <tr>
-      <td>DUT-OMRON †</td>
-      <td style="text-align: right;">0.792</td>
-      <td style="text-align: right;"><strong>0.901</strong></td>
-      <td style="text-align: right;">+0.109</td>
-    </tr>
-    <tr>
-      <td colspan="4"><strong>Camouflage</strong></td>
-    </tr>
-    <tr>
-      <td>COD10K-TE</td>
-      <td style="text-align: right;">0.787</td>
-      <td style="text-align: right;"><strong>0.934</strong></td>
-      <td style="text-align: right;">+0.148</td>
-    </tr>
-    <tr>
-      <td>CAMO-TE</td>
-      <td style="text-align: right;">0.827</td>
-      <td style="text-align: right;"><strong>0.914</strong></td>
-      <td style="text-align: right;">+0.086</td>
-    </tr>
-  </tbody>
-</table>
+
+<img width="33%" src="https://cdn-uploads.huggingface.co/production/uploads/6527e89a8808d80ccff88b7a/x93Ond7tAw8aoLYkucUQn.png"/>
 
 † No sibling in the training mix. DAVIS-S and DUT-OMRON are the two fully cross-domain splits here,
 so they are the pair to read for generalization — and MultiMatte's best absolute score lands on