Minimizing Labeling Effort for Tree Skeleton Segmentation using an Automated Iterative Training Methodology
This addresses the labeling bottleneck for semantic segmentation in agricultural applications, though it appears incremental as an automation of existing human-in-the-loop methods.
The paper tackles the problem of reducing human labeling effort for semantic segmentation by proposing an automated iterative training methodology called Automating-the-Loop, which achieves comparable performance to manual labeling while drastically reducing labeling effort in detecting partially occluded apple trees.
Training of convolutional neural networks for semantic segmentation requires accurate pixel-wise labeling which requires large amounts of human effort. The human-in-the-loop method reduces labeling effort; however, it requires human intervention for each image. This paper describes a general iterative training methodology for semantic segmentation, Automating-the-Loop. This aims to replicate the manual adjustments of the human-in-the-loop method with an automated process, hence, drastically reducing labeling effort. Using the application of detecting partially occluded apple tree segmentation, we compare manually labeled annotations, self-training, human-in-the-loop, and Automating-the-Loop methods in both the quality of the trained convolutional neural networks, and the effort needed to create them. The convolutional neural network (U-Net) performance is analyzed using traditional metrics and a new metric, Complete Grid Scan, which promotes connectivity and low noise. It is shown that in our application, the new Automating-the-Loop method greatly reduces the labeling effort while producing comparable performance to both human-in-the-loop and complete manual labeling methods.