<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ship-Detection on DeepLearning.Earth</title><link>https://deeplearning.earth/tags/ship-detection/</link><description>Recent content in Ship-Detection on DeepLearning.Earth</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Thu, 25 Jun 2026 09:00:00 +0700</lastBuildDate><atom:link href="https://deeplearning.earth/tags/ship-detection/index.xml" rel="self" type="application/rss+xml"/><item><title>Zero-shot Ship detection on a Copernicus Sentinel-2 tile with Oriented R-CNN</title><link>https://deeplearning.earth/posts/2026-06-25_zero-shot_ship_detection_on_a_copernicus_sentinel-2_tile_with_oriented_rcnn/</link><pubDate>Thu, 25 Jun 2026 09:00:00 +0700</pubDate><guid>https://deeplearning.earth/posts/2026-06-25_zero-shot_ship_detection_on_a_copernicus_sentinel-2_tile_with_oriented_rcnn/</guid><description>How far can a DOTA-pretrained oriented detector go on real Sentinel-2 imagery without any fine-tuning?
We took a single 10 m true-colour crop from Copernicus Sentinel-2 — a busy patch of open water with ships at many headings — and ran it through the Oriented R-CNN model shipped with oriented-det. No maritime labels. No changes to the weights. Just a public checkpoint, a satellite tile, and a few inference knobs.</description></item></channel></rss>