Attention-Based Lightweight YOLOv8 Underwater Target Recognition Algorithm

Shun Cheng, Zhiqian Wang, Shaojin Liu, Yan Han, Pengtao Sun, Jianrong Li, Wenling Li · 2024

Read Attention-Based Lightweight YOLOv8 Underwater Target Recognition Algorithm by Shun Cheng, Zhiqian Wang, Shaojin Liu, Yan Han, Pengtao Sun, Jianrong Li, Wenling Li (2024) 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-11645042.txt.

Description

Shun Cheng and co-authors present a leaner underwater object detector in this 2024 paper. Finding objects underwater is hard, and detectors must be fast and accurate on small hardware. Their model reworks the popular YOLOv8 design in four places: a faster feature extractor, an attention block that sharpens pixel calls, a cheaper downsampling step, and a new box loss.

On two underwater datasets, the slim model beat the baseline it grew from, reaching accuracy in the high eighties on one set. It also ran at high frame rates with fewer parameters and less compute. The authors aim it at edge devices on underwater vehicles.

Catalog record

CREATORShun Cheng, Zhiqian Wang, Shaojin Liu, Yan Han, Pengtao Sun, Jianrong Li, Wenling Li
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE49 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11645042

Browse the full library · About the Tower of Babel