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

Source: [EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion](<https://www.sota2.com/research/paper/68fa6a551e209131cea2775c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:10:45.754Z

Authors: Chia-Yuan Chang, Shuo-En Chang, Pei-Yung Hsiao, Li-Chen Fu

Published: 2020-03-23T09:11:44.000Z

## Abstract

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).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Panoptic Segmentation on COCO (test-dev)](<https://www.sota2.com/research/sota/panoptic-segmentation-on-coco-test-dev.md>): Panoptic Segmentation; COCO (test-dev); PQ: 38.9.

- [Panoptic Segmentation on COCO (val)](<https://www.sota2.com/research/sota/panoptic-segmentation-on-coco-val.md>): Panoptic Segmentation; COCO (val); PQ: 38.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2003.10142>)

[PDF](<https://arxiv.org/pdf/2003.10142.pdf>)

[Implementation](<https://www.sota2.com/github.com/neo85824/epsnet>)