REFINE: Prediction Fusion Network for Panoptic Segmentation

Panoptic segmentation aims at generating pixel-wise class and instance predictions for each pixel in the input image, which is a challenging task far more complicated than naively fusing semantic results. Prediction fusion therefore important to achieve accurate panoptic segmentation. In this paper, we present REFINE, pREdiction FusIon NEtwork segmentation, high-quality by improving cross-task prediction fusion, within-task fusion. Our single-model ResNeXt-101 with DCN achieves PQ=51.5 on COCO dataset, surpassing state-of-the-art performance convincing margin comparable ensembled models. smaller model ResNet-50 backbone PQ=44.9, methods larger backbones.