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.
Original languageEnglish
Publication date26 Apr 2020
Publication statusPublished - 26 Apr 2020
EventICLR 2020 Workshop on Computer Vision for Agriculture (CV4A) - Virtual
Duration: 26 Apr 202026 Apr 2020


WorkshopICLR 2020 Workshop on Computer Vision for Agriculture (CV4A)
Internet address

Bibliographical note

Paper presented at the ICLR 2020 Workshop on Computer Vision for Agriculture (CV4A)

Fingerprint Dive into the research topics of 'Evaluation of Model Selection for Kernel Fragment Recognition in Corn Silage'. Together they form a unique fingerprint.

Cite this