Real-Time Panoptic Segmentation from Dense Detections

Abstract

Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution. Current state-of-the-art approaches cannot run in real-time, and simplifying these architectures to improve efficiency severely degrades their accuracy. In this paper, we propose a new single-shot panoptic segmentation network that leverages dense detections and a global self-attention mechanism to operate in real-time with performance approaching the state of the art. We introduce a novel parameter-free mask construction method that substantially reduces computational complexity by efficiently reusing information from the object detection and semantic segmentation sub-tasks. The resulting network has a simple data flow that does not require feature map re-sampling or clustering post-processing, enabling significant hardware acceleration. Our experiments on the Cityscapes and COCO benchmarks show that our network works at 30 FPS on 1024x2048 resolution, trading a 3% relative performance degradation from the current state of the art for up to 440% faster inference.

12 pages, 6 figures

References in corpus (11)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• YOLOv3: An Incremental Improvement
• FCOS: Fully Convolutional One-Stage Object Detection
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Semantic Instance Segmentation with a Discriminative Loss Function
• DeeperLab: Single-Shot Image Parser
• Bridging Category-level and Instance-level Semantic Image Segmentation
• Learning to Fuse Things and Stuff
• PolarMask: Single Shot Instance Segmentation with Polar Representation
• SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
• Explicit Shape Encoding for Real-Time Instance Segmentation