Standardizing and Centralizing Datasets for Efficient Training of Agricultural Deep Learning Models.

In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural datasets. This lack of agriculture-specific fine-tuning potentially increases training time and resource use, and decreases model performance, leading to an overall decrease in data efficiency. To overcome this limitation, we collect a wide range of existing public datasets for 3 distinct tasks, standardize them, and construct standard training and evaluation pipelines, providing us with a set of benchmarks and pretrained models. We then conduct a number of experiments using methods that are commonly used in deep learning tasks but unexplored in their domain-specific applications for agriculture. Our experiments guide us in developing a number of approaches to improve data efficiency when training agricultural deep learning models, without large-scale modifications to existing pipelines. Our results demonstrate that even slight training modifications, such as using agricultural pretrained model weights, or adopting specific spatial augmentations into data processing pipelines, can considerably boost model performance and result in shorter convergence time, saving training resources. Furthermore, we find that even models trained on low-quality annotations can produce comparable levels of performance to their high-quality equivalents, suggesting that datasets with poor annotations can still be used for training, expanding the pool of currently available datasets. Our methods are broadly applicable throughout agricultural deep learning and present high potential for substantial data efficiency improvements.

Behavior of the renal kallikrein in spontaneously hypertensive rats: Influence of sexual hormones and aldosterone-sensitive distal nephron ion channels.

The renal kallikrein-kinin system (RKKS) has been related to blood pressure control and sodium and water balance. We have previously shown that female spontaneously hypertensive rats (SHR) have high urinary kallikrein activity (UKa) and lower blood pressure (BP) than males whereas ovariectomy stimulates UKa and diminishes BP. We also showed that high K+ intake and prepuberal gonadectomy (Gx) diminish BP with a concomitant increase in UKa and plasma aldosterone levels. Since kallikrein co-localize in the same distal nephron segments of aldosterone effectors, we explored the effect of pharmacological blockage of aldosterone receptor, epithelial Na+ (ENaC) and the rectifying outer medulla K+ (ROMK) channels in different gonad contexts on the gene expression, renal tissue content and urine release of kallikrein. Klk1 gene expression was determined by real-time PCR and enzymatic activity of kallikrein by the amidolytic method. We found that the inhibition of the aldosterone receptor by spironolactone increases kallikrein renal tissue storage and decreases its urinary activity, especially in Gx rats. Moreover, ENaC blockade by benzamil increases the renal content of kallikrein without affecting synthesis or excretion, especially in females and Gx animals, while the inhibition of ROMK by glibenclamide increases the synthesis and renal content of kallikrein only in intact male animals. We concluded that RKKS regulation showed sexual dimorphism and seemed to be modulated by sex hormones throughout a process involving aldosterone and the aldosterone-sensitive ion channels..