Comprehensive Saliency Fusion for Object Co-segmentation

TL;DR

This paper introduces a comprehensive saliency fusion method for object co-segmentation that combines saliency maps within and across images using deep learning, significantly improving results on benchmark datasets.

Contribution

It proposes a novel fusion approach that integrates intra- and inter-image saliency maps with deep learning, advancing beyond prior methods that used handcrafted features.

Findings

Achieves superior co-segmentation accuracy on iCoseg, MSRC, and Internet Images datasets.

Outperforms previous methods in benchmark evaluations.

Demonstrates the effectiveness of deep learning in saliency fusion for co-segmentation.

Abstract

Object co-segmentation has drawn significant attention in recent years, thanks to its clarity on the expected foreground, the shared object in a group of images. Saliency fusion has been one of the promising ways to carry it out. However, prior works either fuse saliency maps of the same image or saliency maps of different images to extract the expected foregrounds. Also, they rely on hand-crafted saliency extraction and correspondence processes in most cases. This paper revisits the problem and proposes fusing saliency maps of both the same image and different images. It also leverages advances in deep learning for the saliency extraction and correspondence processes. Hence, we call it comprehensive saliency fusion. Our experiments reveal that our approach achieves much-improved object co-segmentation results compared to prior works on important benchmark datasets such as iCoseg, MSRC, and Internet Images.