# One-Shot Segmentation in Clutter

arXiv: https://arxiv.org/abs/1803.09597 · HTML: https://mlsanity.com/paper/1803.09597/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2018.

## Built on by (most cited first, 7 of 7)

- [One-Shot Affordance Detection](https://mlsanity.com/paper/2106.14747/) (2021)
- [ILIAS: Instance-Level Image retrieval At Scale](https://mlsanity.com/paper/2502.11748/) (2025)
- [AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection](https://mlsanity.com/paper/2209.10904/) (2022)
- [Few-Shot Video Object Detection](https://mlsanity.com/paper/2104.14805/) (2021)
- [Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild](https://mlsanity.com/paper/2109.11874/) (2021)
- [An Ensemble Learning Approach towards Waste Segmentation in Cluttered Environment](https://mlsanity.com/paper/2602.13681/) (2026)
- [Prototypical Region Proposal Networks for Few-Shot Localization and Classification](https://mlsanity.com/paper/2104.03496/) (2021)

## Abstract (arXiv)

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 textitcluttered 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 textitMaskNet, 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.