Evaluation of Model Selection for Kernel Fragment Recognition in Corn Silage
This work addresses model selection challenges for farmers to improve silage quality during harvesting, but it is incremental as it focuses on optimizing existing methods for a specific domain.
The paper tackled the problem of model selection for kernel fragment recognition in corn silage by evaluating state-of-the-art CNN models, showing accuracy improvements with complex meta-architectures and speed optimization by reducing image size with minimal accuracy loss. It achieved up to a 20 percentage point increase in Average Precision at IoU 0.5 while decreasing inference time compared to prior work.
Model selection when designing deep learning systems for specific use-cases can be a challenging task as many options exist and it can be difficult to know the trade-off between them. Therefore, we investigate a number of state of the art CNN models for the task of measuring kernel fragmentation in harvested corn silage. The models are evaluated across a number of feature extractors and image sizes in order to determine optimal model design choices based upon the trade-off between model complexity, accuracy and speed. We show that accuracy improvements can be made with more complex meta-architectures and speed can be optimised by decreasing the image size with only slight losses in accuracy. Additionally, we show improvements in Average Precision at an Intersection over Union of 0.5 of up to 20 percentage points while also decreasing inference time in comparison to previously published work. This result for better model selection enables opportunities for creating systems that can aid farmers in improving their silage quality while harvesting.