[IPOL announce] new article: On the Domain Generalization Capabilities of Interactive Segmentation Methods

[announcements about the IPOL journal]

A new article is available in IPOL: https://www.ipol.im/pub/art/2024/499/

Franco Marchesoni-Acland, Tanguy Magne, Fayçal Rekbi, and Gabriele 
Facciolo,
On the Domain Generalization Capabilities of Interactive Segmentation 
Methods,
Image Processing On Line, 14 (2024), pp. 25–40.
https://doi.org/10.5201/ipol.2024.499

Abstract
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.