Papers › One-Shot Segmentation in Clutter

One-Shot Segmentation in Clutter

26 Mar 2018ICML 2018 7arXiv:1803.09597archive 2025-07-28

Claudio Michaelis, Matthias Bethge, Alexander S. Ecker

We tackle the problem of one-shot segmentation: finding and segmenting a previously unseen object in a cluttered scene based on a single instruction example. We propose a novel dataset, which we call cluttered Omniglot. Using a baseline architecture combining a Siamese embedding for detection with a U-net for segmentation we show that increasing levels of clutter make the task progressively harder. Using oracle models with access to various amounts of ground-truth information, we evaluate different aspects of the problem and show that in this kind of visual search task, detection and segmentation are two intertwined problems, the solution to each of which helps solving the other. We therefore introduce MaskNet, an improved model that attends to multiple candidate locations, generates segmentation proposals to mask out background clutter and selects among the segmented objects. Our findings suggest that such image recognition models based on an iterative refinement of object detection and foreground segmentation may provide a way to deal with highly cluttered scenes.

PaperPDFConference PDFCode

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

Code

michaelisc/cluttered-omniglot officialmentioned in papermentioned on GitHubtfMIT 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

Foreground SegmentationOne-Shot SegmentationSegmentationobject-detection

Datasets

Introduced by this paper, per the archive.

Cluttered Omniglot

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
One-Shot Segmentation Cluttered Omniglot MaskNet IoU [256 distractors] 43.7 #1 of 2 Archive leaderboard report
One-Shot Segmentation Cluttered Omniglot MaskNet IoU [32 distractors] 65.6 #1 of 2 Archive leaderboard report
One-Shot Segmentation Cluttered Omniglot MaskNet IoU [4 distractors] 95.8 #1 of 2 Archive leaderboard report
One-Shot Segmentation Cluttered Omniglot Siamese-U-Net IoU [256 distractors] 38.4 #2 of 2 Archive leaderboard report
One-Shot Segmentation Cluttered Omniglot Siamese-U-Net IoU [32 distractors] 62.4 #2 of 2 Archive leaderboard report
One-Shot Segmentation Cluttered Omniglot Siamese-U-Net IoU [4 distractors] 97.1 #2 of 2 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

Concatenated Skip ConnectionConvolutionMax PoolingReLUU-Net

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