Papers › f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation

f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation

28 Jan 2020CVPR 2020 6arXiv:2001.10331archive 2025-07-28

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 .

PaperPDFConference PDFCode

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.

For agents, on Syntology's MCP service (how to connect):

Code

jpconnel/fbrs-segmentation mentioned on GitHubpytorchSyntology: not harvested report
PaddlePaddle/PaddleSeg paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow (arXiv:2109.09406; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Interactive SegmentationSegmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
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

Spatial Broadcast Decoder

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