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

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

23 Mar 2020arXiv:2003.10142archive 2025-07-28

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

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).

Paper PDF Code

Code

neo85824/epsnet officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance Segmentation Panoptic Segmentation Scene Parsing Segmentation Semantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Panoptic Segmentation	COCO test-dev	EPSNet (ResNet-101-FPN)	PQ	38.9	#34 of 38	Archive leaderboard	report
Panoptic Segmentation	COCO test-dev	EPSNet (ResNet-101-FPN)	PQst	31.0	#34 of 38	Archive leaderboard	report
Panoptic Segmentation	COCO test-dev	EPSNet (ResNet-101-FPN)	PQth	44.1	#34 of 38	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution Global Average Pooling Kaiming Initialization Max Pooling ReLU Residual Block Residual Connection SPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections