Bridging the Domain Gap: Transfer Learning and Aggressive Fine-Tuning for Robust Plant Disease Detection in Low-Resource African Agriculture

Sunday Aspita Abraham, Abidemi Adeniyi, Qurrat Ul Ain Mughal, Odunayo Olanloye
Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments, PMLR 319:16-25, 2026.

Abstract

Farmers across Sub-Saharan Africa lose harvests to diseases they cannot name. By the time leaf spots are obvious, the damage is done. Deep learning models such as CNN excel on benchmark datasets, yet when brought to a real farm in southwestern Nigeria during harmattan season—when exposed to factors such as dust, glare, and soil clutter—they fall apart. Field data were gathered in Ibadan and surrounding districts of Oyo and Osun States, totalling 1,742 photographs. Starting from ImageNet-pretrained MobileNetV2, naive fine-tuning helps a little, but not nearly enough. The real lift comes from a two-step training protocol with an auto-fallback safeguard. Tomato accuracy climbs from 34.69% to 97.96%; cassava goes from 52.42% to 98.39%. In low-resource agriculture, the bottleneck is not architecture, but training discipline.

Cite this Paper

BibTeX
@InProceedings{pmlr-v319-abraham26a, title = {Bridging the Domain Gap: Transfer Learning and Aggressive Fine-Tuning for Robust Plant Disease Detection in Low-Resource African Agriculture}, author = {Abraham, Sunday Aspita and Adeniyi, Abidemi and Mughal, Qurrat Ul Ain and Olanloye, Odunayo}, booktitle = {Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments}, pages = {16--25}, year = {2026}, editor = {Folorunso, Sakinat and Ogundokun, Roseline and Oladipo, Francisca}, volume = {319}, series = {Proceedings of Machine Learning Research}, month = {11--14 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v319/main/assets/abraham26a/abraham26a.pdf}, url = {https://proceedings.mlr.press/v319/abraham26a.html}, abstract = {Farmers across Sub-Saharan Africa lose harvests to diseases they cannot name. By the time leaf spots are obvious, the damage is done. Deep learning models such as CNN excel on benchmark datasets, yet when brought to a real farm in southwestern Nigeria during harmattan season—when exposed to factors such as dust, glare, and soil clutter—they fall apart. Field data were gathered in Ibadan and surrounding districts of Oyo and Osun States, totalling 1,742 photographs. Starting from ImageNet-pretrained MobileNetV2, naive fine-tuning helps a little, but not nearly enough. The real lift comes from a two-step training protocol with an auto-fallback safeguard. Tomato accuracy climbs from 34.69% to 97.96%; cassava goes from 52.42% to 98.39%. In low-resource agriculture, the bottleneck is not architecture, but training discipline.} }
Endnote
%0 Conference Paper %T Bridging the Domain Gap: Transfer Learning and Aggressive Fine-Tuning for Robust Plant Disease Detection in Low-Resource African Agriculture %A Sunday Aspita Abraham %A Abidemi Adeniyi %A Qurrat Ul Ain Mughal %A Odunayo Olanloye %B Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments %C Proceedings of Machine Learning Research %D 2026 %E Sakinat Folorunso %E Roseline Ogundokun %E Francisca Oladipo %F pmlr-v319-abraham26a %I PMLR %P 16--25 %U https://proceedings.mlr.press/v319/abraham26a.html %V 319 %X Farmers across Sub-Saharan Africa lose harvests to diseases they cannot name. By the time leaf spots are obvious, the damage is done. Deep learning models such as CNN excel on benchmark datasets, yet when brought to a real farm in southwestern Nigeria during harmattan season—when exposed to factors such as dust, glare, and soil clutter—they fall apart. Field data were gathered in Ibadan and surrounding districts of Oyo and Osun States, totalling 1,742 photographs. Starting from ImageNet-pretrained MobileNetV2, naive fine-tuning helps a little, but not nearly enough. The real lift comes from a two-step training protocol with an auto-fallback safeguard. Tomato accuracy climbs from 34.69% to 97.96%; cassava goes from 52.42% to 98.39%. In low-resource agriculture, the bottleneck is not architecture, but training discipline.
APA
Abraham, S.A., Adeniyi, A., Mughal, Q.U.A. & Olanloye, O.. (2026). Bridging the Domain Gap: Transfer Learning and Aggressive Fine-Tuning for Robust Plant Disease Detection in Low-Resource African Agriculture. Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments, in Proceedings of Machine Learning Research 319:16-25 Available from https://proceedings.mlr.press/v319/abraham26a.html.

Related Material