Papers › Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach

Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach

6 Jun 2021NeurIPS 2021 12arXiv:2106.03188archive 2025-07-28

Ahmed Abbas, Paul Swoboda

We propose a fully differentiable architecture for simultaneous semantic and instance segmentation (a.k.a. panoptic segmentation) consisting of a convolutional neural network and an asymmetric multiway cut problem solver. The latter solves a combinatorial optimization problem that elegantly incorporates semantic and boundary predictions to produce a panoptic labeling. Our formulation allows to directly maximize a smooth surrogate of the panoptic quality metric by backpropagating the gradient through the optimization problem. Experimental evaluation shows improvement by backpropagating through the optimization problem w.r.t. comparable approaches on Cityscapes and COCO datasets. Overall, our approach shows the utility of using combinatorial optimization in tandem with deep learning in a challenging large scale real-world problem and showcases benefits and insights into training such an architecture.

PaperPDFConference PDFCode

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

Code

aabbas90/COPS officialmentioned in papermentioned on GitHubpytorch report
LPMP/LPMP mentioned 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

Combinatorial OptimizationInstance SegmentationPanoptic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Segmentation COCO test-dev COPS (ResNet-50) PQ 38.5 #35 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev COPS (ResNet-50) PQst 34.8 #35 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev COPS (ResNet-50) PQth 41.0 #35 of 38 Archive leaderboard report
Panoptic Segmentation Cityscapes test COPS (ResNet-50) PQ 60 #9 of 10 Archive leaderboard report
Panoptic Segmentation Cityscapes val COPS (ResNet-50) AP 34.1 #20 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val COPS (ResNet-50) PQ 62.1 #20 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val COPS (ResNet-50) PQst 67.2 #20 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val COPS (ResNet-50) PQth 55.1 #20 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val COPS (ResNet-50) mIoU 79.3 #20 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.

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