Minimizing Labeling Effort for Tree Skeleton Segmentation using an Automated Iterative Training Methodology

TL;DR

This paper introduces an automated iterative training methodology called Automating-the-Loop for semantic segmentation, significantly reducing labeling effort while maintaining high performance, demonstrated on apple tree segmentation.

Contribution

The paper presents a novel automated iterative training process that replicates human-in-the-loop adjustments, reducing manual labeling effort in semantic segmentation tasks.

Findings

Automating-the-Loop reduces labeling effort significantly.

The method achieves comparable segmentation performance to manual labeling.

A new metric, Complete Grid Scan, evaluates connectivity and noise in segmentation.

Abstract

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.