On the Domain Generalization Capabilities of Interactive Segmentation Methods
Franco Marchesoni-Acland, Tanguy Magne, Fayçal Rekbi, Gabriele Facciolo
⚠ This is a preprint. It may change before it is accepted for publication.


Interactive image segmentation (IIS) methods are usually trained over segmentation datasets containing natural images. They are also usually evaluated over natural images. However, the most common use case is the annotation of new images from a different domain. Yet, the performance of IIS methods on a different domain is seldom reported. In this work, we evaluate a state-of-the-art IIS method trained with natural images over an aerial image dataset. Its performance is compared to the performances the method achieves when being trained/finetuned with aerial images. The comparison reveals that there is a big domain generalization gap.

This is an MLBriefs article, the source code has not been reviewed!
The original source code is available here (last checked 2023/09/12).