TagLab: A human-centric AI system for interactive semantic segmentation

TL;DR

TagLab is an open-source AI-assisted tool designed for interactive semantic segmentation of large orthoimages, combining automation and human control to improve annotation speed and accuracy across scientific disciplines.

Contribution

It introduces a flexible, human-centric annotation system that integrates assisted tools, custom automatic models, and quick editing features for diverse scientific applications.

Findings

Speeds up image annotation in marine ecology and architectural heritage.

Enhances accuracy with human-in-the-loop segmentation.

Flexible pipeline adaptable to various scientific domains.

Abstract

Fully automatic semantic segmentation of highly specific semantic classes and complex shapes may not meet the accuracy standards demanded by scientists. In such cases, human-centered AI solutions, able to assist operators while preserving human control over complex tasks, are a good trade-off to speed up image labeling while maintaining high accuracy levels. TagLab is an open-source AI-assisted software for annotating large orthoimages which takes advantage of different degrees of automation; it speeds up image annotation from scratch through assisted tools, creates custom fully automatic semantic segmentation models, and, finally, allows the quick edits of automatic predictions. Since the orthoimages analysis applies to several scientific disciplines, TagLab has been designed with a flexible labeling pipeline. We report our results in two different scenarios, marine ecology, and architectural heritage.