We lifted 14 functions out of this paper's own repositories and ran 9 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| wang-yuyan/warmstart-graphcut-algorithms-pulic | canonical | 9 of 14 |
| Function | Status | Where it lives |
|---|---|---|
| BuildRdGraph | Ran | wang-yuyan/warmstart-graphcut-algorithms-pulic/warmstart.py code served (permissive licence) · get_code("9caa32f382144cdf") |
| FeasRestoreIter | Ran | wang-yuyan/warmstart-graphcut-algorithms-pulic/warmstart.py code served (permissive licence) · get_code("d5056df8184a3828") |
| augmentingPath | Ran | wang-yuyan/warmstart-graphcut-algorithms-pulic/augmentingPath.py code served (permissive licence) · get_code("4565367ba2062c7d") |
| bfs | Ran | wang-yuyan/warmstart-graphcut-algorithms-pulic/augmentingPath.py code served (permissive licence) · get_code("fa75a7ef81db9995") |
| boundaryPenalty | Ran | wang-yuyan/warmstart-graphcut-algorithms-pulic/imagesegmentation.py code served (permissive licence) · get_code("8f2f97d37d13e7ed") |
| dfs | Ran | wang-yuyan/warmstart-graphcut-algorithms-pulic/augmentingPath.py code served (permissive licence) · get_code("e503655d38845884") |
| mstd | Ran | wang-yuyan/warmstart-graphcut-algorithms-pulic/average.py code served (permissive licence) · get_code("c36b61954251cd64") |
| push | Ran | wang-yuyan/warmstart-graphcut-algorithms-pulic/pushRelabel.py code served (permissive licence) · get_code("cc70b0d45ca32bce") |
| pushRelabel | Ran | wang-yuyan/warmstart-graphcut-algorithms-pulic/pushRelabel.py code served (permissive licence) · get_code("a0f01ea78ec163a4") |
| FeasProj | Not yet run | wang-yuyan/warmstart-graphcut-algorithms-pulic/warmstart.py code served (permissive licence) · get_code("0b65a3917226501d") |
| ScaleSeeds | Not yet run | wang-yuyan/warmstart-graphcut-algorithms-pulic/imagesegmentation.py code served (permissive licence) · get_code("faab442a2eb7d75e") |
| imagegroup | Not yet run | wang-yuyan/warmstart-graphcut-algorithms-pulic/image_cropping.py code served (permissive licence) · get_code("764f69dd2a5f0acc") |
| overFlowVertex | Not yet run | wang-yuyan/warmstart-graphcut-algorithms-pulic/pushRelabel.py code served (permissive licence) · get_code("939fc9bacea838a5") |
| plantSeed | Not yet run | wang-yuyan/warmstart-graphcut-algorithms-pulic/imagesegmentation.py code served (permissive licence) · get_code("01e05df240c864e8") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent work has shown that leveraging learned predictions can improve the running time of algorithms for bipartite matching and similar combinatorial problems. In this work, we build on this idea to improve the performance of the widely used Ford-Fulkerson algorithm for computing maximum flows by seeding Ford-Fulkerson with predicted flows. Our proposed method offers strong theoretical performance in terms of the quality of the prediction. We then consider image segmentation, a common use-case of flows in computer vision, and complement our theoretical analysis with strong empirical results.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.00837")
get_code_for_paper("2303.00837")
have("2303.00837")
Connect an agent — have() is free.