Dann, ChristophChristophDannGehler, PeterPeterGehlerRoth, StefanStefanRothNowozin, SebastianSebastianNowozin2022-03-122022-03-122012https://publica.fraunhofer.de/handle/publica/37849910.1007/978-3-642-32717-9_40We present a novel conditional random field (CRF) for semantic segmentation that extends the common Potts model of spatial coherency with latent topics, which capture higher-order spatial relations of segment labels. Specifically, we show how recent approaches for producing sets of figure-ground segmentations can be leveraged to construct a suitable graph representation for this task. The CRF model incorporates such proposal segmentations as topics, modelling the joint occurrence or absence of object classes. The resulting model is trained using a structured large margin approach with latent variables. Experimental results on the challenging VOC'10 dataset demonstrate significant performance improvements over simpler models with less spatial structure.enimage processingimage segmentationsemantic labelinggraph representationForschungsgruppe Visual Inference (VINF)006conference paper