Attention based deep feature fusion for hyperspectral target detection

Masoud Amiri, Maryam Imani, Hassan Ghassemian · 2025

Read Attention based deep feature fusion for hyperspectral target detection by Masoud Amiri, Maryam Imani, Hassan Ghassemian (2025) 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-12789635.txt.

Description

Masoud Amiri, Maryam Imani, and Hassan Ghassemian present in 2025 a deep feature fusion frame for finding targets in hyperspectral images. Such images carry many color bands, which makes target search hard amid varied backgrounds and few target samples. Class imbalance adds to the strain.

Their frame joins two branches in small image patches. One branch uses attention to catch links within and across patches, while the other pulls local space-color patterns. Self and cross attention steer focus toward likely target zones. A guided filter cleans the output maps. Tests on four benchmarks beat top past methods, with gains up to fifteen percent.

Catalog record

CREATORMasoud Amiri, Maryam Imani, Hassan Ghassemian
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE139 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12789635

Browse the full library · About the Tower of Babel