Enhancing the weed segmentation in diverse crop fields using computationally effective concatenated attention U-Net with convolutional block attention module
R Arumuga Arun, S Umamaheswari, Islabudeen Mohamed Meerasha, B Mohankumar · 2025
Read Enhancing the weed segmentation in diverse crop fields using computationally effective concatenated attention U-Net with convolutional block attention module by R Arumuga Arun, S Umamaheswari, Islabudeen Mohamed Meerasha, B Mohankumar (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-12804821.txt.
Description
Arumuga Arun and co-authors present in 2025 a light computer model that finds weeds in crop fields. Weeds steal water and food from crops, but spraying a whole field wastes chemicals and harms soil. A model that marks weeds in images can guide treatment only where it is needed, if it can run on small farm devices.
Their model joins attention blocks that help it focus on weed areas, while using steps that cut the cost of computing. They trained it on three data sets from varied crop fields. The aim is sharp marking of crops and weeds without a heavy model that small devices cannot run.
Catalog record
| CREATOR | R Arumuga Arun, S Umamaheswari, Islabudeen Mohamed Meerasha, B Mohankumar |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |