Update multi_class_non_max_suppression.py (keras-team#1318)

* Update multi_class_non_max_suppression.py

This will give much better results aesthetically to our users.

* Update multi_class_non_max_suppression.py

Author: LukeWood

keras_cv/layers/object_detection/multi_class_non_max_suppression.py

@@ -31,7 +31,7 @@ class MultiClassNonMaxSuppression(tf.keras.layers.Layer):
         IoU threshold for two boxes to be considered same for suppression. Defaults
         to 0.5.
       confidence_threshold: a float value in the range [0, 1]. All boxes with
-        confidence below this value will be discarded. Defaults to 0.05.
+        confidence below this value will be discarded. Defaults to 0.9.
       max_detections: the maximum detections to consider after nms is applied. A large
         number may trigger significant memory overhead. Defaults to 100.
       max_detections_per_class: the maximum detections to consider per class after
@@ -43,7 +43,7 @@ def __init__(
         bounding_box_format,
         from_logits,
         iou_threshold=0.5,
-        confidence_threshold=0.5,
+        confidence_threshold=0.9,
         max_detections=100,
         max_detections_per_class=100,
         **kwargs,