MFK-Net: a computationally efficient Mamba-Fourier-KAN hybrid architecture for UAV-based crop classification
Yanze Mu · 2026
Read MFK-Net: a computationally efficient Mamba-Fourier-KAN hybrid architecture for UAV-based crop classification by Yanze Mu (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-13547254.txt.
Description
Sorting crops from drone photos helps farmers and food monitors, but fine crop classes and cluttered fields strain most models. Yanze Mu proposes MFK-Net, a 2026 network that blends three design ideas to stay fast and accurate.
One part reads long-range patterns with an efficient state-space backbone. A second part sharpens texture and edges by filtering in the frequency domain. A third part, built on spline-based networks, draws the final class borders. On a public drone benchmark of more than seven thousand images, the model reached accuracy above ninety-three percent, beating three known rivals at modest size. Extra tests on plant disease and forest photos showed it transfers well to new tasks.
Catalog record
| CREATOR | Yanze Mu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 89 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |