CFNet: Learning Correlation Functions for One-Stage Panoptic Segmentation. (arXiv:2201.04796v1 [cs.CV])

Recently, there is growing attention on one-stage panoptic segmentation
methods which aim to segment instances and stuff jointly within a fully
convolutional pipeline efficiently. However, most of the existing works
directly feed the backbone features to various segmentation heads ignoring the
demands for semantic and instance segmentation are different: The former needs
semantic-level discriminative features, while the latter requires features to
be distinguishable across instances. To alleviate this, we propose to first
predict semantic-level and instance-level correlations among different
locations …

arxiv correlation cv learning segmentation stage