# Segmenting Ships in Satellite Imagery With Squeeze and Excitation U-Net

Source: [Segmenting Ships in Satellite Imagery With Squeeze and Excitation U-Net](<https://www.sota2.com/research/paper/68fa66901e209131cea10e8e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:52:21.192Z

Authors: Venkatesh R, Anand Metha

Published: 2019-10-27T08:28:51.000Z

## Abstract

The ship-detection task in satellite imagery presents significant obstacles to even the most state of the art segmentation models due to lack of labelled dataset or approaches which are not able to generalize to unseen images. The most common methods for semantic segmentation involve complex two-stage networks or networks which make use of a multi-scale scene parsing module. In this paper, we propose a modified version of the popular U-Net architecture called Squeeze and Excitation U-Net and train it with a loss that helps in directly optimizing the intersection over union (IoU) score. Our method gives comparable performance to other methods while having the additional benefit of being computationally efficient.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1910.12206>)

[PDF](<https://arxiv.org/pdf/1910.12206.pdf>)