Metraipolis › archive › dc_c5313fa4c293

FedXCrop: Privacy-Preserving Crop Disease Detection via Federated Learning with Post-Aggregation Explainability under Non-IID Farm Distributions — arXiv:2611.06221

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06221
License (as archived)
CC0-1.0
Archived
2026-11-05T18:30:00.491Z
SHA-256 of the archived text
f0ea5787bd5f6e46376ee7bc9dff32e79f6a1a5cb54c948e533d0c50b5d4e68c
Stable URL of this page
https://metraipolis.com/documento/dc_c5313fa4c293

How to cite

FedXCrop: Privacy-Preserving Crop Disease Detection via Federated Learning with Post-Aggregation Explainability under Non-IID Farm Distributions — arXiv:2611.06221 — arXiv (en), https://arxiv.org/abs/2611.06221 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c5313fa4c293 (Metraipolis archive dc_c5313fa4c293, sha256 f0ea5787bd5f6e46376ee7bc9dff32e79f6a1a5cb54c948e533d0c50b5d4e68c)
BibTeX
@misc{dcc5313fa4c293,
  title = {FedXCrop: Privacy-Preserving Crop Disease Detection via Federated Learning with Post-Aggregation Explainability under Non-IID Farm Distributions — arXiv:2611.06221},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06221},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c5313fa4c293; sha256 f0ea5787bd5f6e46376ee7bc9dff32e79f6a1a5cb54c948e533d0c50b5d4e68c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06221. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep learning can classify crop diseases accurately from benchmark leaf images, but centralized training requires farms to share raw data, and predictions without explanations offer limited support for treatment decisions. We present FedXCrop, a federated crop disease classification pipeline that quantitatively evaluates explanations of the aggregated global model. A MobileNetV2 model trained centrally on PlantVillage achieved 99.38% test accuracy (standard deviation 0.05 over three seeds) on a fixed test set of 5,428 images across 38 classes. Federated models initialized with ImageNet weights were trained for 30 rounds across five clients. FedAvg achieved 98.81% accuracy with identically distributed clients and 98.81%, 98.59%, and 97.78% under Dirichlet label skew (alpha = 1, 0.5, and 0.1, respectively). FedProx was not significantly different from FedAvg at any heterogeneity level (McNemar p > 0.3). Grad-CAM and SmoothGrad explanations were evaluated on 380 test images. Both attributed more energy to the leaf than chance (0.70-0.78 versus 0.60), while Grad-CAM maps from federated and centralized models showed Spearman correlations of 0.74-0.76. Agreement decreased as heterogeneity increased, lesion localization was only modestly above chance, and a model-randomization test indicated that SmoothGrad maps depended substantially on image structure rather than learned parameters. In this setting, label skew reduced federated accuracy by 0.6-1.6 percentage points relative to centralized training. FedAvg largely preserved Grad-CAM behavior, while FedProx provided no measurable benefit.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.06221 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-05T18:19:49.055Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).