# Object Discovery via Cohesion Measurement

## TL;DR

This paper introduces a novel affinity matrix and cohesion measurement for robust object discovery in images, effectively handling color distortions and improving saliency detection and object proposal generation.

## Contribution

It formulates a new affinity matrix resilient to color distortions and derives a cohesion measurement, enabling a new spectral clustering-based object discovery method.

## Key findings

- Achieved promising results on benchmark datasets.
- Improved robustness to color distortions in object discovery.
- Enhanced performance in saliency detection and object proposal tasks.

## Abstract

Color and intensity are two important components in an image. Usually, groups of image pixels, which are similar in color or intensity, are an informative representation for an object. They are therefore particularly suitable for computer vision tasks, such as saliency detection and object proposal generation. However, image pixels, which share a similar real-world color, may be quite different since colors are often distorted by intensity. In this paper, we reinvestigate the affinity matrices originally used in image segmentation methods based on spectral clustering. A new affinity matrix, which is robust to color distortions, is formulated for object discovery. Moreover, a Cohesion Measurement (CM) for object regions is also derived based on the formulated affinity matrix. Based on the new Cohesion Measurement, a novel object discovery method is proposed to discover objects latent in an image by utilizing the eigenvectors of the affinity matrix. Then we apply the proposed method to both saliency detection and object proposal generation. Experimental results on several evaluation benchmarks demonstrate that the proposed CM based method has achieved promising performance for these two tasks.