Updated method part with current Bayesian filtering process

Signed-off-by: Jim Martens <github@2martens.de>

body.tex

@@ -574,7 +574,9 @@ varying classifications are averaged into multiple lower confidence
 values which should increase the entropy and, hence, flag an
 observation for removal.
 
-The final step is a top \(k\) selection.
+The remainder of the filtering follows the vanilla SSD procedure: per-class
+confidence threshold, non-maximum suppression, and a top \(k\) selection
+at the end.
 
 \chapter{Experimental Setup and Results}