SALC-Net: A lightweight contour-preserving segmentation network for yak body segmentation in complex grazing environments

Wang Zhang, Changqi Fu, Jiayi Xing, Shilei Xing, Dedong Gao, Qiangqiang Yao · 2026

Read SALC-Net: A lightweight contour-preserving segmentation network for yak body segmentation in complex grazing environments by Wang Zhang, Changqi Fu, Jiayi Xing, Shilei Xing, Dedong Gao, Qiangqiang Yao (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/plos-pone-0353672.txt.

Description

Wang Zhang and co-authors build in 2026 a light segmentation network that traces yak body outlines in messy high pasture scenes for automated livestock checks. Outline accuracy matters for later shape analysis, yet light networks often lose borders on soft, moving animals and must run on small edge devices. Their design pairs a slim image backbone with modules that adapt view size cheaply and rebuild outlines across scales.

On a custom high altitude yak dataset the network reached high overlap accuracy while running well above real time speed. The balance of speed and border care makes it practical for smart pasture tools that cannot carry heavy models.

Catalog record

CREATORWang Zhang, Changqi Fu, Jiayi Xing, Shilei Xing, Dedong Gao, Qiangqiang Yao
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE31977
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0353672

Browse the full library · About the Tower of Babel