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

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.

References in corpus (11)

• Deep Residual Learning for Image Recognition
• Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
• Semantic Segmentation using Adversarial Networks
• Automated Pavement Crack Segmentation Using U-Net-based Convolutional Neural Network
• An Overview of Deep Semi-Supervised Learning
• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• Fruit Detection, Segmentation and 3D Visualisation of Environments in Apple Orchards
• Annotating Object Instances with a Polygon-RNN
• On the influence of Dice loss function in multi-class organ segmentation of abdominal CT using 3D fully convolutional networks
• Semantic Segmentation for Partially Occluded Apple Trees Based on Deep Learning
• Uncertainty-Driven Semantic Segmentation through Human-Machine Collaborative Learning