Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces FecalFed, a federated learning framework for poultry disease classification from fecal images, addressing data privacy concerns and data silos in agricultural settings. They curate and release a deduplicated dataset, poultry-fecal-fl, and evaluate FecalFed under heterogeneous, non-IID conditions to simulate realistic farm environments. Results show that FecalFed, using FedAdam with a Swin-Small architecture, achieves 90.31% accuracy, approaching centralized performance while preserving privacy, and an edge-optimized Swin-Tiny model maintains 89.74% accuracy.
Federated learning can overcome data heterogeneity and privacy constraints to achieve near-centralized performance in poultry disease detection, even with edge-optimized models.
Early detection of highly pathogenic avian influenza (HPAI) and endemic poultry diseases is critical for global food security. While computer vision models excel at classifying diseases from fecal imaging, deploying these systems at scale is bottlenecked by farm data privacy concerns and institutional data silos. Furthermore, existing open-source agricultural datasets frequently suffer from severe, undocumented data contamination. In this paper, we introduce $\textbf{FecalFed}$, a privacy-preserving federated learning framework for poultry disease classification. We first curate and release $\texttt{poultry-fecal-fl}$, a rigorously deduplicated dataset of 8,770 unique images across four disease classes, revealing and eliminating a 46.89$\%$ duplication rate in popular public repositories. To simulate realistic agricultural environments, we evaluate FecalFed under highly heterogeneous, non-IID conditions (Dirichlet $\alpha=0.5$). While isolated single-farm training collapses under this data heterogeneity, yielding only 64.86$\%$ accuracy, our federated approach recovers performance without centralizing sensitive data. Specifically, utilizing server-side adaptive optimization (FedAdam) with a Swin-Small architecture achieves 90.31$\%$ accuracy, closely approaching the centralized upper bound of 95.10\%. Furthermore, we demonstrate that an edge-optimized Swin-Tiny model maintains highly competitive performance at 89.74$\%$, establishing a highly efficient, privacy-first blueprint for on-farm avian disease monitoring.