Open set segmentation is a relatively new and unexplored task, with just a handful of methods proposed to model such tasks. We propose a novel method called CoReSeg that tackles the issue using class conditioned reconstruction of the input images according to their pixelwise mask. Our method conditions each input pixel to all known classes, expecting higher errors for pixels of unknown classes. It was observed that the proposed method produces better semantic consistency in its predictions than the baselines, resulting in cleaner segmentation maps that better fit object boundaries. CoRe-Seg outperforms state-of-the-art methods on the Vaihingen and Potsdam ISPRS datasets, while also being competitive on the Houston 2018 IEEE GRSS Data Fusion dataset. Our official implementation for CoReSeg is available at: https: //github.com/iannunes/CoReSeg.
Open set segmentation is a relatively new and unexplored task, with just a handful of methods proposed to model such tasks. We propose a novel method called CoReSeg that tackles the issue using class conditional reconstruction of the input images according to their pixelwise mask. Our method conditions each input pixel to all known classes, expecting higher errors for pixels of unknown classes. It was observed that the proposed method produces better semantic consistency in its predictions, resulting in cleaner segmentation maps that better fit object boundaries. CoRe-Seg outperforms state-of-the-art methods on the Vaihingen and Potsdam ISPRS datasets, while also being competitive on the Houston 2018 IEEE GRSS Data Fusion dataset. Official implementation for CoReSeg is available at: https://github.com/iannunes/CoReSeg.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.