Learning an interactive segmentation system

By Hannes Nickisch, Pushmeet Kohli, Carsten Rother. 2009

29 citations recorded by the source corpus.

Many successful applications of computer vision to image or video manipulation are interactive by nature. However, parameters of such systems are often trained neglecting the user. Traditionally, interactive systems have been treated in the same manner as their fully automatic counterparts. Their performance is evaluated by computing the accuracy of their solutions under some fixed set of user interactions. This paper proposes a new evaluation and learning method which brings the user in the loop. It is based on the use of an active robot user -- a simulated model of a human user. We show how this approach can be used to evaluate and learn parameters of state-of-the-art interactive segmentation systems. We also show how simulated user models can be integrated into the popular max-margin method for parameter learning and propose an algorithm to solve the resulting optimisation problem.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Getting to 99% Accuracy in Interactive Segmentation (2020, methodology): “All convolutional layers are followed by LeakyRelu activations [38]. dled together, we propose to introduce the clicks sequentially, starting from a single click, and adopting the same sequential scheme used to evaluate interactive segmentation algorithms [6, 9–13, 35, 39].”
Iterative Interaction Training for Segmentation Editing Networks (2018, positive): “The robot user we utilized for training the network is based on the model introduced by Nickisch et al. [10].”
UI-Net: Interactive Artificial Neural Networks for Iterative Image Segmentation Based on a User Model (2017, unknown): “Alternatively, the model can be de-ﬁned by a rule-based system such as [NRKR10, ZND ∗ 11] or the one proposed here.”
Geodesic star convexity for interactive image segmentation (2010, methodology): “We evaluate interactive segmentation systems quantitatively by means of a “robot user” [14].”