Papers › Weakly- and Semi-Supervised Panoptic Segmentation

Weakly- and Semi-Supervised Panoptic Segmentation

10 Aug 2018ECCV 2018 9arXiv:1808.03575archive 2025-07-28

Qizhu Li, Anurag Arnab, Philip H. S. Torr

We present a weakly supervised model that jointly performs both semantic- and instance-segmentation -- a particularly relevant problem given the substantial cost of obtaining pixel-perfect annotation for these tasks. In contrast to many popular instance segmentation approaches based on object detectors, our method does not predict any overlapping instances. Moreover, we are able to segment both "thing" and "stuff" classes, and thus explain all the pixels in the image. "Thing" classes are weakly-supervised with bounding boxes, and "stuff" with image-level tags. We obtain state-of-the-art results on Pascal VOC, for both full and weak supervision (which achieves about 95% of fully-supervised performance). Furthermore, we present the first weakly-supervised results on Cityscapes for both semantic- and instance-segmentation. Finally, we use our weakly supervised framework to analyse the relationship between annotation quality and predictive performance, which is of interest to dataset creators.

Paper PDF Conference PDF Code

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

Code

qizhuli/Weakly-Supervised-Panoptic-Segmentation officialmentioned in papermentioned on GitHubMIT 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 Segmentation Semantic Segmentation Weakly-Supervised Semantic Segmentation Weakly-supervised instance segmentation Weakly-supervised panoptic segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Panoptic Segmentation	Cityscapes val	Dynamically Instantiated Network (ResNet-101)	AP	28.6	#34 of 37	Archive leaderboard	report
Panoptic Segmentation	Cityscapes val	Dynamically Instantiated Network (ResNet-101)	PQ	53.8	#34 of 37	Archive leaderboard	report
Panoptic Segmentation	Cityscapes val	Dynamically Instantiated Network (ResNet-101)	PQst	62.1	#34 of 37	Archive leaderboard	report
Panoptic Segmentation	Cityscapes val	Dynamically Instantiated Network (ResNet-101)	PQth	42.5	#34 of 37	Archive leaderboard	report
Panoptic Segmentation	Cityscapes val	Dynamically Instantiated Network (ResNet-101)	mIoU	79.8	#34 of 37	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

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