Interactive Image Segmentation Using Constrained Dominant Sets

TL;DR

This paper introduces a novel interactive image segmentation method leveraging constrained dominant sets, enabling effective segmentation from various user inputs and robustly handling noisy annotations, with demonstrated superior performance on benchmark datasets.

Contribution

The paper presents a new graph-theoretic segmentation approach using constrained dominant sets that generalizes maximal cliques, adaptable to different input modalities and noise conditions.

Findings

Outperforms state-of-the-art algorithms on benchmark datasets

Effectively handles diverse input modalities including scribbles and bounding boxes

Robust to noisy user annotations

Abstract

We propose a new approach to interactive image segmentation based on some properties of a family of quadratic optimization problems related to dominant sets, a well-known graph-theoretic notion of a cluster which generalizes the concept of a maximal clique to edge-weighted graphs. In particular, we show that by properly controlling a regularization parameter which determines the structure and the scale of the underlying problem, we are in a position to extract groups of dominant-set clusters which are constrained to contain user-selected elements. The resulting algorithm can deal naturally with any type of input modality, including scribbles, sloppy contours, and bounding boxes, and is able to robustly handle noisy annotations on the part of the user. Experiments on standard benchmark datasets show the effectiveness of our approach as compared to state-of-the-art algorithms on a variety of natural images under several input conditions.