Papers › Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

25 Mar 2020arXiv:2003.11657archive 2025-07-28

Michal Rolínek, Paul Swoboda, Dominik Zietlow, Anselm Paulus, Vít Musil, Georg Martius

Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contains unmodified combinatorial solvers. Using the presence of heavily optimized combinatorial solvers together with some improvements in architecture design, we advance state-of-the-art on deep graph matching benchmarks for keypoint correspondence. In addition, we highlight the conceptual advantages of incorporating solvers into deep learning architectures, such as the possibility of post-processing with a strong multi-graph matching solver or the indifference to changes in the training setting. Finally, we propose two new challenging experimental setups. The code is available at https://github.com/martius-lab/blackbox-deep-graph-matching

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2003.11657")

Code

Syntology Ran 5 of 11 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · violated contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 11 samples from 2 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

martius-lab/blackbox-deep-graph-matching officialmentioned in papermentioned on GitHubpytorch report
LPMP/LPMP mentioned on GitHubpytorch report
martius-lab/blackbox-backprop mentioned on GitHubpytorchMIT report
q3erf/topo_bbgm 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

11 samples harvested; 5 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
3ran · our draft was wrong
1ran · fixture could not drive it
6unverified

Licence: 3 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

concat_features Thinklab-SJTU/ThinkMatch/models/BBGM/model.py community (archive-listed) ran · fixture could not drive it licence not identified · pointer only · bc40b9897e027ece · report
lexico_iter Thinklab-SJTU/ThinkMatch/models/BBGM/model.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · a81be531136a1b00 · report
normalize_over_channels Thinklab-SJTU/ThinkMatch/models/BBGM/model.py community (archive-listed) ran · violated contract fingerprinted licence not identified · pointer only · f12ddebef47d400e · report
rank martius-lab/blackbox-backprop/blackbox_backprop/ranking.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 2e1e2e8c543195f7 · report
rank_normalised martius-lab/blackbox-backprop/blackbox_backprop/ranking.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · ed49cae4f66fd45c · report
darker martius-lab/blackbox-backprop/visualization_utils.py community (archive-listed) unverified MIT (permissive) · b9da24f59f9a500a · report
dijkstra martius-lab/blackbox-backprop/blackbox_backprop/shortest_path.py community (archive-listed) unverified MIT (permissive) · 79d845c43088342b · report
gurobi_tsp martius-lab/blackbox-backprop/blackbox_backprop/travelling_salesman.py community (archive-listed) unverified MIT (permissive) · 8073153564d8de8e · report
interpolate martius-lab/blackbox-backprop/visualization_utils.py community (archive-listed) unverified MIT (permissive) · 7a3fc706eff98f36 · report
maybe_parallelize martius-lab/blackbox-backprop/blackbox_backprop/utils.py community (archive-listed) unverified MIT (permissive) · f4d8af262e615db7 · report
subtour martius-lab/blackbox-backprop/blackbox_backprop/travelling_salesman.py community (archive-listed) unverified MIT (permissive) · c08e18b8412b9339 · report

Tasks

Combinatorial OptimizationDeep LearningGraph Matching

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Matching PASCAL VOC BBGM-Multi F1 score 0.628 #2 of 31 Archive leaderboard report
Graph Matching PASCAL VOC BBGM F1 score 0.614 #5 of 31 Archive leaderboard report
Graph Matching PASCAL VOC BBGM matching accuracy 0.801 #5 of 31 Archive leaderboard report
Graph Matching SPair-71k BBGM matching accuracy 0.8215 #5 of 8 Archive leaderboard report
Graph Matching Willow Object Class BBGM matching accuracy 0.9718 #10 of 23 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