# LooseCut: Interactive Image Segmentation with Loosely Bounded Boxes

arXiv: https://arxiv.org/abs/1507.03060 · HTML: https://mlsanity.com/paper/1507.03060/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2015.

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

- [Focused and Collaborative Feedback Integration for Interactive Image Segmentation](https://mlsanity.com/paper/2303.11880/) (2023)
- [DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer](https://mlsanity.com/paper/2304.06668/) (2023)
- [Probabilistic Attention for Interactive Segmentation](https://mlsanity.com/paper/2106.15338/) (2021)
- [Interactive Segmentation for Diverse Gesture Types Without Context](https://mlsanity.com/paper/2307.10518/) (2023)
- [PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentation](https://mlsanity.com/paper/2306.06656/) (2023)
- [A Baseline Statistical Method For Robust User-Assisted Multiple Segmentation](https://mlsanity.com/paper/2201.02779/) (2022)
- [Variance-insensitive and Target-preserving Mask Refinement for Interactive Image Segmentation](https://mlsanity.com/paper/2312.14387/) (2023)

## Abstract (arXiv)

One popular approach to interactively segment the foreground object of interest from an image is to annotate a bounding box that covers the foreground object. Then, a binary labeling is performed to achieve a refined segmentation. One major issue of the existing algorithms for such interactive image segmentation is their preference of an input bounding box that tightly encloses the foreground object. This increases the annotation burden, and prevents these algorithms from utilizing automatically detected bounding boxes. In this paper, we develop a new LooseCut algorithm that can handle cases where the input bounding box only loosely covers the foreground object. We propose a new Markov Random Fields (MRF) model for segmentation with loosely bounded boxes, including a global similarity constraint to better distinguish the foreground and background, and an additional energy term to encourage consistent labeling of similar-appearance pixels. This MRF model is then solved by an iterated max-flow algorithm. In the experiments, we evaluate LooseCut in three publicly-available image datasets, and compare its performance against several state-of-the-art interactive image segmentation algorithms. We also show that LooseCut can be used for enhancing the performance of unsupervised video segmentation and image saliency detection.