# EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion

arXiv: https://arxiv.org/abs/2003.10142 · HTML: https://mlsanity.com/paper/2003.10142/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2020.

## Built on by (most cited first, 6 of 6)

- [Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments](https://mlsanity.com/paper/2207.04526/) (2022)
- [Panoptic Segmentation: A Review](https://mlsanity.com/paper/2111.10250/) (2021)
- [Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation](https://mlsanity.com/paper/2404.03799/) (2024)
- [SE-PSNet: Silhouette-based Enhancement Feature for Panoptic Segmentation Network](https://mlsanity.com/paper/2107.05093/) (2021)
- [What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studies](https://mlsanity.com/paper/2507.06513/) (2025)
- [CFNet: Learning Correlation Functions for One-Stage Panoptic Segmentation](https://mlsanity.com/paper/2201.04796/) (2022)

## Abstract (arXiv)

Panoptic segmentation is a scene parsing task which unifies semantic segmentation and instance segmentation into one single task. However, the current state-of-the-art studies did not take too much concern on inference time. In this work, we propose an Efficient Panoptic Segmentation Network (EPSNet) to tackle the panoptic segmentation tasks with fast inference speed. Basically, EPSNet generates masks based on simple linear combination of prototype masks and mask coefficients. The light-weight network branches for instance segmentation and semantic segmentation only need to predict mask coefficients and produce masks with the shared prototypes predicted by prototype network branch. Furthermore, to enhance the quality of shared prototypes, we adopt a module called "cross-layer attention fusion module", which aggregates the multi-scale features with attention mechanism helping them capture the long-range dependencies between each other. To validate the proposed work, we have conducted various experiments on the challenging COCO panoptic dataset, which achieve highly promising performance with significantly faster inference speed (53ms on GPU).