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.
@article{arxiv.1910.04751,
title = {Panoptic-DeepLab},
author = {Bowen Cheng and Maxwell D. Collins and Yukun Zhu and Ting Liu and Thomas S. Huang and Hartwig Adam and Liang-Chieh Chen},
journal= {arXiv preprint arXiv:1910.04751},
year = {2019}
}
Comments
This work is presented at ICCV 2019 Joint COCO and Mapillary Recognition Challenge Workshop