Papers › Information-Theoretic Segmentation by Inpainting Error Maximization

Information-Theoretic Segmentation by Inpainting Error Maximization

14 Dec 2020CVPR 2021 1arXiv:2012.07287archive 2025-07-28

Pedro Savarese, Sunnie S. Y. Kim, Michael Maire, Greg Shakhnarovich, David Mcallester

We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets. More specifically, we group image pixels into foreground and background, with the goal of minimizing predictability of one set from the other. An easily computed loss drives a greedy search process to maximize inpainting error over these partitions. Our method does not involve training deep networks, is computationally cheap, class-agnostic, and even applicable in isolation to a single unlabeled image. Experiments demonstrate that it achieves a new state-of-the-art in unsupervised segmentation quality, while being substantially faster and more general than competing approaches.

PaperPDFConference PDFCode

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

Code

lolemacs/iem officialmentioned in papermentioned on GitHub 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

Image SegmentationSegmentationSemantic SegmentationUnsupervised Image Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Inpainting

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