<ul><li>The study investigates the impact of recurrency in existing image segmentation models.</li><li>Different types of recurrency, including self-organizing, relational, and memory retrieval, are explored.</li><li>Experiments are conducted on artificial and medical imaging data with high levels of noise and few-shot learning settings.</li><li>The results do not support the hypothesis that recurrent models perform better in these settings, suggesting further research is needed.</li></ul>

The Role of Recurrency in Image Segmentation for Noisy and Limited Sample Settings

Discover more