# Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation

arXiv: https://arxiv.org/abs/2009.13342 · HTML: https://mlsanity.com/paper/2009.13342/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision](https://mlsanity.com/paper/2108.07682/) (2021)
- [MGNet: Monocular Geometric Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2206.13199/) (2022)
- [Panoptic Segmentation: A Review](https://mlsanity.com/paper/2111.10250/) (2021)
- [PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation](https://mlsanity.com/paper/2206.00468/) (2022)
- [Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentation](https://mlsanity.com/paper/2204.05370/) (2022)
- [CFNet: Learning Correlation Functions for One-Stage Panoptic Segmentation](https://mlsanity.com/paper/2201.04796/) (2022)
- [SUNet: Scale-aware Unified Network for Panoptic Segmentation](https://mlsanity.com/paper/2209.02877/) (2022)
- [MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation](https://mlsanity.com/paper/2605.12640/) (2026)
- [Rethinking Air-Ground Collaboration: A Progressive Cross-Task Benchmark and Socialized Learning Framework](https://mlsanity.com/paper/2606.18841/) (2026)

## Abstract (arXiv)

Panoptic segmentation (PS) is a complex scene understanding task that requires providing high-quality segmentation for both thing objects and stuff regions. Previous methods handle these two classes with semantic and instance segmentation modules separately, following with heuristic fusion or additional modules to resolve the conflicts between the two outputs. This work simplifies this pipeline of PS by consistently modeling the two classes with a novel PS framework, which extends a detection model with an extra module to predict category- and instance-aware pixel embedding (CIAE). CIAE is a novel pixel-wise embedding feature that encodes both semantic-classification and instance-distinction information. At the inference process, PS results are simply derived by assigning each pixel to a detected instance or a stuff class according to the learned embedding. Our method not only demonstrates fast inference speed but also the first one-stage method to achieve comparable performance to two-stage methods on the challenging COCO benchmark.