Panoptic-DeepLab
This work addresses the problem of panoptic segmentation for computer vision applications, representing an incremental improvement with strong specific gains.
The paper tackles panoptic segmentation by proposing Panoptic-DeepLab, a bottom-up and single-shot approach that achieves state-of-the-art results, including 84.2% mIoU, 39.0% AP, and 65.5% PQ on the Cityscapes test set.
We present Panoptic-DeepLab, a bottom-up and single-shot approach for panoptic segmentation. Our Panoptic-DeepLab is conceptually simple and delivers state-of-the-art results. In particular, we adopt the dual-ASPP and dual-decoder structures specific to semantic, and instance segmentation, respectively. The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e.g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression. Our single Panoptic-DeepLab sets the new state-of-art at all three Cityscapes benchmarks, reaching 84.2% mIoU, 39.0% AP, and 65.5% PQ on test set, and advances results on the other challenging Mapillary Vistas.