Loosecut: Interactive image segmentation with loosely bounded boxes
By Hongkai Yu, Youjie Zhou, Hui Qian, Min Xian, Song Wang. 2015
46 citations recorded by the source corpus.
One popular approach to interactively segment an object of interest from an image is to annotate a bounding box that covers the object, followed by a binary labeling. However, the existing algorithms for such interactive image segmentation prefer a bounding box that tightly encloses the 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 bounding box only loosely covers the object. We propose a new Markov Random Fields (MRF) model for segmentation with loosely bounded boxes, including an additional energy term to encourage consistent labeling of similar-appearance pixels and a global similarity constraint to better distinguish the foreground and background. This MRF model is then solved by an iterated max-flow algorithm. We evaluate LooseCut in three public image datasets, and show its better performance against several state-of-the-art methods when increasing the bounding-box size.
Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Bernt Schiele
- Xiaogang Wang
- Ming-Hsuan Yang
- Jitendra Malik
- Dacheng Tao
- Trevor Darrell
- Philip H. S. Torr
In Human-Computer Interaction
Citations in the corpus
- Iteratively Trained Interactive Segmentation (2018, methodology): “[29] further optimise the results for the problem of interactive segmentation by developing an algorithm called LooseCut.”
- Simple Does It: Weakly Supervised Instance and Semantic Segmentation (2016, methodology): “Similarly, given a bounding box (e.g. selected by a detector), GrabCut [36] variants can be used to obtain an instance segmentation (e.g. [22, 7, 41, 40, 47]).”