Align code with polygon-only training

docs/registry/elements/ship.md

@@ -2,9 +2,9 @@
 id: ship
 type: element
 name: Ship
-task_types: [detection, instance_segmentation, oriented_detection]
-preferred_heads: [validity, context, detection, instance]
-label_formats: [bbox, rotated_bbox, polygon, coco, dota]
+task_types: [polygon_extraction, instance_segmentation, oriented_polygon]
+preferred_heads: [validity, context, polygon, instance]
+label_formats: [polygon, coco, dota]
 positive_label: ship
 negative_policy: unlabeled_is_ignore
 typical_sensors: [PMS, PAN, SAR]
@@ -14,11 +14,9 @@ typical_resolutions_m: [0.5, 1, 2, 3, 10]
 # Ship
 
 Ships are object targets and should not be forced into a pure semantic
-segmentation class. Use detection, oriented detection, or instance segmentation
-when annotations support it.
+segmentation class. Use polygon or instance heads when annotations support it.
 
 ## Required Context
 
 - Ports, aquaculture grids, bridges, and bright wave wakes are hard negatives.
 - SAR and optical ship extraction should be sensor-aware.
-