Papers › f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation
f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation
Konstantin Sofiiuk, Ilia Petrov, Olga Barinova, Anton Konushin
Deep neural networks have become a mainstream approach to interactive segmentation. As we show in our experiments, while for some images a trained network provides accurate segmentation result with just a few clicks, for some unknown objects it cannot achieve satisfactory result even with a large amount of user input. Recently proposed backpropagating refinement (BRS) scheme introduces an optimization problem for interactive segmentation that results in significantly better performance for the hard cases. At the same time, BRS requires running forward and backward pass through a deep network several times that leads to significantly increased computational budget per click compared to other methods. We propose f-BRS (feature backpropagating refinement scheme) that solves an optimization problem with respect to auxiliary variables instead of the network inputs, and requires running forward and backward pass just for a small part of a network. Experiments on GrabCut, Berkeley, DAVIS and SBD datasets set new state-of-the-art at an order of magnitude lower time per click compared to original BRS. The code and trained models are available at https://github.com/saic-vul/fbrs_interactive_segmentation .
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Interactive Segmentation | Berkeley | f-BRS-B (ResNet-50) | NoC@90 | 4.34 | #11 of 14 | Archive leaderboard | report |
| Interactive Segmentation | DAVIS | f-BRS-B (ResNet-101) | NoC@85 | 5.04 | #10 of 15 | Archive leaderboard | report |
| Interactive Segmentation | DAVIS | f-BRS-B (ResNet-101) | NoC@90 | 7.41 | #10 of 15 | Archive leaderboard | report |
| Interactive Segmentation | GrabCut | f-BRS-B (ResNet-34) | NoC@85 | 2 | #10 of 18 | Archive leaderboard | report |
| Interactive Segmentation | GrabCut | f-BRS-B (ResNet-34) | NoC@90 | 2.46 | #10 of 18 | Archive leaderboard | report |
| Interactive Segmentation | SBD | f-BRS-B (ResNet-101) | NoC@85 | 4.81 | #8 of 14 | Archive leaderboard | report |
| Interactive Segmentation | SBD | f-BRS-B (ResNet-101) | NoC@90 | 7.73 | #8 of 14 | 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
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