TagLab: A human-centric AI system for interactive semantic segmentation
This system addresses the need for accurate and efficient image annotation in scientific disciplines where fully automatic methods fall short, offering a flexible and interactive solution.
The authors tackled the problem of achieving high-accuracy semantic segmentation for complex shapes and specific classes by developing TagLab, a human-centric AI system that assists operators in image annotation, resulting in faster labeling while maintaining high accuracy levels, with applications demonstrated in marine ecology and architectural heritage.
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.