# Instance-Level Relative Saliency Ranking with Graph Reasoning

Source: [Instance-Level Relative Saliency Ranking with Graph Reasoning](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27add>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:23:37.152Z

Authors: Nian Liu, Long Li, Wangbo Zhao, Junwei Han, Ling Shao

Published: 2021-07-08T13:10:42.000Z

## Abstract

Conventional salient object detection models cannot differentiate the importance of different salient objects. Recently, two works have been proposed to detect saliency ranking by assigning different degrees of saliency to different objects. However, one of these models cannot differentiate object instances and the other focuses more on sequential attention shift order inference. In this paper, we investigate a practical problem setting that requires simultaneously segment salient instances and infer their relative saliency rank order. We present a novel unified model as the first end-to-end solution, where an improved Mask R-CNN is first used to segment salient instances and a saliency ranking branch is then added to infer the relative saliency. For relative saliency ranking, we build a new graph reasoning module by combining four graphs to incorporate the instance interaction relation, local contrast, global contrast, and a high-level semantic prior, respectively. A novel loss function is also proposed to effectively train the saliency ranking branch. Besides, a new dataset and an evaluation metric are proposed for this task, aiming at pushing forward this field of research. Finally, experimental results demonstrate that our proposed model is more effective than previous methods. We also show an example of its practical usage on adaptive image retargeting.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Saliency Ranking on IRSR (test)](<https://www.sota2.com/research/sota/saliency-ranking-on-irsr-test.md>): Saliency Ranking; IRSR (test); SA-SOR: 0.565.

- [Saliency Ranking on ASSR (test)](<https://www.sota2.com/research/sota/saliency-ranking-on-assr-test.md>): Saliency Ranking; ASSR (test); SOR: 81.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2107.03824>)

[PDF](<https://arxiv.org/pdf/2107.03824.pdf>)