TinyBayes delivers 78.7% accuracy on cocoa disease detection with a 9.5 MB edge pipeline that uses YOLOv8-Nano, MobileNetV3-Small, and a closed-form Jacobi-DMR Bayesian classifier.
CNN features off-the-shelf: An astounding baseline for recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TinyBayes: Closed-Form Bayesian Inference via Jacobi Prior for Real-Time Image Classification on Edge Devices
TinyBayes delivers 78.7% accuracy on cocoa disease detection with a 9.5 MB edge pipeline that uses YOLOv8-Nano, MobileNetV3-Small, and a closed-form Jacobi-DMR Bayesian classifier.