Edge-Aware Attention with Shallow-Guided Fusion for Ship Detection in Remote Sensing

Haiyang He, Liang Dong · 2026

Read Edge-Aware Attention with Shallow-Guided Fusion for Ship Detection in Remote Sensing by Haiyang He, Liang Dong (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13611236.txt.

Description

Haiyang He and Liang Dong proposed this 2026 method for spotting ships in satellite images. Ships are small, sparse, and set against busy sea and coast backgrounds. Fast detectors often miss them or place them poorly. The team improved a real-time detection model at the level where image features are first formed.

One new module feeds an edge map into the attention step, so sharp outlines like hulls, coasts, and wakes draw more focus. A learnable dial sets how strong that pull is. A second module blends fine shallow detail with deep features, keeping small ships visible. Together the changes aim at better accuracy without losing speed. The work serves sea traffic watch, port running, and defense uses.

Catalog record

CREATORHaiyang He, Liang Dong
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE58 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13611236

Browse the full library · About the Tower of Babel