Reliability Scores from Saliency Map Clusters for Improved Image-based Harvest-Readiness Prediction in Cauliflower
This work addresses the challenge of automated harvest timing for cauliflower farmers, but it is incremental as it builds on existing deep learning methods with interpretability techniques.
The paper tackled the problem of accurately predicting cauliflower harvest-readiness from images by analyzing classifier reliability using saliency map clusters, achieving a 15.72% improvement in overall accuracy to 88.14% and a 15.44% improvement in average class accuracy to 88.52%.
Cauliflower is a hand-harvested crop that must fulfill high-quality standards in sales making the timing of harvest important. However, accurately determining harvest-readiness can be challenging due to the cauliflower head being covered by its canopy. While deep learning enables automated harvest-readiness estimation, errors can occur due to field-variability and limited training data. In this paper, we analyze the reliability of a harvest-readiness classifier with interpretable machine learning. By identifying clusters of saliency maps, we derive reliability scores for each classification result using knowledge about the domain and the image properties. For unseen data, the reliability can be used to (i) inform farmers to improve their decision-making and (ii) increase the model prediction accuracy. Using RGB images of single cauliflower plants at different developmental stages from the GrowliFlower dataset, we investigate various saliency mapping approaches and find that they result in different quality of reliability scores. With the most suitable interpretation tool, we adjust the classification result and achieve a 15.72% improvement of the overall accuracy to 88.14% and a 15.44% improvement of the average class accuracy to 88.52% for the GrowliFlower dataset.