EfficientPS: Efficient Panoptic Segmentation

Understanding the scene in which an autonomous robot operates is critical for its competent functioning. Such scene comprehension necessitates recognizing instances of traffic participants along with general scene semantics which can be effectively addressed by the panoptic segmentation task. In this paper, we introduce the Efficient Panoptic Segmentation (EfficientPS) architecture that consists of a shared backbone which efficiently encodes and fuses semantically rich multi-scale features. We incorporate a new semantic head that aggregates fine and contextual features coherently and a new variant of Mask R-CNN as the instance head. We also propose a novel panoptic fusion module that congruously integrates the output logits from both the heads of our EfficientPS architecture to yield the final panoptic segmentation output. Additionally, we introduce the KITTI panoptic segmentation dataset that contains panoptic annotations for the popularly challenging KITTI benchmark. Extensive evaluations on Cityscapes, KITTI, Mapillary Vistas and Indian Driving Dataset demonstrate that our proposed architecture consistently sets the new state-of-the-art on all these four benchmarks while being the most efficient and fast panoptic segmentation architecture to date.

Automated summary

This paper introduces an Efficient Panoptic Segmentation (EfficientPS) architecture that efficiently encodes and fuses semantically rich multi-scale features for scene comprehension, setting new state-of-the-art performance on multiple benchmarks. The architecture incorporates a new semantic head, a Mask R-CNN variant as the instance head, and a novel panoptic fusion module to integrate output logits for final panoptic segmentation. Additionally, a new KITTI panoptic segmentation dataset is introduced, demonstrating the efficiency and competitiveness of the proposed architecture.