Papers › Getting to 99% Accuracy in Interactive Segmentation

Getting to 99% Accuracy in Interactive Segmentation

17 Mar 2020arXiv:2003.07932archive 2025-07-28

Marco Forte, Brian Price, Scott Cohen, Ning Xu, François Pitié

Interactive object cutout tools are the cornerstone of the image editing workflow. Recent deep-learning based interactive segmentation algorithms have made significant progress in handling complex images and rough binary selections can typically be obtained with just a few clicks. Yet, deep learning techniques tend to plateau once this rough selection has been reached. In this work, we interpret this plateau as the inability of current algorithms to sufficiently leverage each user interaction and also as the limitations of current training/testing datasets. We propose a novel interactive architecture and a novel training scheme that are both tailored to better exploit the user workflow. We also show that significant improvements can be further gained by introducing a synthetic training dataset that is specifically designed for complex object boundaries. Comprehensive experiments support our approach, and our network achieves state of the art performance.

PaperPDFCode

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

Code

MarcoForte/DeepInteractiveSegmentation mentioned on GitHubpytorch report
MarcoForte/FBA-Matting mentioned on GitHubpytorchMIT report
marcoforte/fba_matting mentioned on GitHubpytorchMIT 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

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

Tasks

Deep LearningInteractive Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Cutout

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