Papers › Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach
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.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Syntology holds a reference implementation of Combinatorial Optimization for Panoptic Segmentation (COPS), generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Combinatorial Optimization for Panoptic Segmentation (COPS)') (how to connect); the free check have('2106.03188') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2106.03188", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2106.03188")
Code
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.
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.
1 assembly on this paper: 0 harvested, 1 generated.
generated Assembly for Combinatorial Optimization for Panoptic Segmentation (COPS) (graph method: Combinatorial Optimization for Panoptic Segmentation (COPS)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).
label matches by construction: the code was generated for this method (not judged by a model)
- total_edge_similarity entry · level 2 · ran ·
ac77d662b879375a18851f951247798b3cb799e1457e3272e25b392049d1ac37
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2106.03188") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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