Deep Learning for Earth Image Segmentation based on Imperfect Polyline Labels with Annotation Errors

TL;DR

This paper introduces a novel EM-based deep learning framework that effectively handles geometric annotation errors in earth image segmentation, significantly improving classification accuracy over existing methods.

Contribution

The paper proposes a new EM algorithm-based framework that jointly updates model parameters and infers true label locations, addressing geometric annotation errors in earth image segmentation.

Findings

Reduces false positives by 67%

Reduces false negatives by 55%

Outperforms baseline methods in accuracy

Abstract

In recent years, deep learning techniques (e.g., U-Net, DeepLab) have achieved tremendous success in image segmentation. The performance of these models heavily relies on high-quality ground truth segment labels. Unfortunately, in many real-world problems, ground truth segment labels often have geometric annotation errors due to manual annotation mistakes, GPS errors, or visually interpreting background imagery at a coarse resolution. Such location errors will significantly impact the training performance of existing deep learning algorithms. Existing research on label errors either models ground truth errors in label semantics (assuming label locations to be correct) or models label location errors with simple square patch shifting. These methods cannot fully incorporate the geometric properties of label location errors. To fill the gap, this paper proposes a generic learning framework based on the EM algorithm to update deep learning model parameters and infer hidden true label locations simultaneously. Evaluations on a real-world hydrological dataset in the streamline refinement application show that the proposed framework outperforms baseline methods in classification accuracy (reducing the number of false positives by 67% and reducing the number of false negatives by 55%).