Abstract
In this paper, we present an efficient solution for weed classification in agriculture. We focus on optimizing model performance at inference while respecting the constraints of the agricultural domain. We propose a Quantized Deep Neural Network model that classifies a dataset of 9 weed classes using 8-bit integer (int8) quantization, a departure from standard 32-bit floating point (fp32) models. Recognizing the hardware resource limitations in agriculture, our model balances model size, inference time, and accuracy, aligning with practical requirements. We evaluate the approach on ResNet-50 and InceptionV3 architectures, comparing their performance against their int8 quantized versions. Transfer learning and fine-tuning are applied using the DeepWeeds dataset. The results show staggering model size and inference time reductions while maintaining accuracy in real-world production scenarios like Desktop, Mobile and Raspberry Pi. Our work sheds light on a promising direction for efficient AI in agriculture, holding potential for broader applications.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 2
Claim · model-written summary
Int8 quantization reduced weed classifier model size relative to fp32 versions.
Verbatim
e0“staggering model size and inference time reductions while maintaining accuracy”
t0“Weed”
e1“standard 32-bit floating point (fp32) models”
Claim · model-written summary
Int8 quantization reduced weed classifier inference time.
Not reportedComparatorValue
Verbatim
e0“staggering model size and inference time reductions while maintaining accuracy”
t0“Weed”