Lightweight Maize Disease Detection through Post-Training Quantization with Similarity Preservation

Carlos Victorino Padeiro, Tse-Wei Chen, Takahiro Komamizu, Ichiro Ide; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 2111-2120

Traditional crop disease diagnosis reliant on expert visual observation is expensive time-consuming and prone to error. While Convolutional Neural Networks (CNNs) offer promising alternatives their high resource demands limit their accessibility to farmers particularly those in resource-constrained settings. Lightweight models that operate on resource-limited devices without network access are crucial to address this gap. This paper proposes a Similarity-Preserving Quantization (SPQ) method to convert high-precision CNNs into lower-precision models while maintaining similar feature representations. While quantization offers a promising approach for building lightweight CNNs for crop disease detection the quality of quantized models often suffers. SPQ addresses this challenge by ensuring equivalent activation patterns for similar crop images in both the original and quantized models. Experimental evaluation using MobileNetV2 and ResNet-50 demonstrates that SPQ improves throughput inference and memory footprint more than 3 times while preserving the detection performance.