Papers › Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network

Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network

6 Sep 2018CoRR 2019 2arXiv:1809.02110archive 2025-07-28

Daan de Geus, Panagiotis Meletis, Gijs Dubbelman

We present a single network method for panoptic segmentation. This method combines the predictions from a jointly trained semantic and instance segmentation network using heuristics. Joint training is the first step towards an end-to-end panoptic segmentation network and is faster and more memory efficient than training and predicting with two networks, as done in previous work. The architecture consists of a ResNet-50 feature extractor shared by the semantic segmentation and instance segmentation branch. For instance segmentation, a Mask R-CNN type of architecture is used, while the semantic segmentation branch is augmented with a Pyramid Pooling Module. Results for this method are submitted to the COCO and Mapillary Joint Recognition Challenge 2018. Our approach achieves a PQ score of 17.6 on the Mapillary Vistas validation set and 27.2 on the COCO test-dev set.

Paper PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Instance Segmentation Panoptic Segmentation Segmentation Semantic Segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Panoptic Segmentation	COCO test-dev	JSIS-Net	PQ	27.2	#38 of 38	Archive leaderboard	report
Panoptic Segmentation	COCO test-dev	JSIS-Net	PQst	23.4	#38 of 38	Archive leaderboard	report
Panoptic Segmentation	COCO test-dev	JSIS-Net	PQth	29.6	#38 of 38	Archive leaderboard	report
Panoptic Segmentation	Mapillary val	JSIS-Net (ResNet-50)	PQ	17.6	#11 of 13	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 Mask R-CNN Max Pooling Pyramid Pooling Module RPN ReLU Residual Block Residual Connection RoIAlign Softmax

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