# Determined by User Needs: A Salient Object Detection Rationale Beyond Conventional Visual Stimuli

Source: [Determined by User Needs: A Salient Object Detection Rationale Beyond Conventional Visual Stimuli](<https://www.sota2.com/research/paper/69d48fa67d0172140ec7441d>)

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

Data updated: 2026-04-08T05:00:04.658Z

Authors: Chenglizhao Chen, Shujian Zhang, Luming Li, Wenfeng Song, Shuai Li

Published: 2026-04-04T00:10:33.000Z

## Abstract

Existing \\textbf{s}alient \\textbf{o}bject \\textbf{d}etection (SOD) methods adopt a \\textbf{passive} visual stimulus-based rationale--objects with the strongest visual stimuli are perceived as the user's primary focus (i.e., salient objects). They ignore the decisive role of users' \\textbf{proactive needs} in segmenting salient objects--if a user has a need before seeing an image, the user's salient objects align with their needs, e.g., if a user's need is \`\`white apple'', when this user sees an image, the user's primary focus is on the \`\`white apple'' or \`\`the most white apple-like'' objects in the image. Such an oversight not only \\textbf{fails to satisfy users}, but also \\textbf{limits the development of downstream tasks}. For instance, in salient object ranking tasks, focusing solely on visual stimuli-based salient objects is insufficient for conducting an analysis of fine-grained relationships between users' viewing order (usually determined by user's needs) and scenes, which may result in wrong ranking results. Clearly, it is essential to detect salient objects based on user needs. Thus, we advocate a \\textbf{User} \\textbf{S}alient \\textbf{O}bject \\textbf{D}etection (UserSOD) task, which focuses on \\textbf{detecting salient objects align with users' proactive needs when user have needs}. The main challenge for this new task is the lack of datasets for model training and testing.

## 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.

- [Salient Object Detection on DUTS](<https://www.sota2.com/research/sota/salient-object-detection-on-duts.md>): Salient Object Detection; DUTS; F-beta Score: 95.7.

- [Salient Object Detection on UserSOD (test)](<https://www.sota2.com/research/sota/salient-object-detection-on-usersod-test.md>): Salient Object Detection; UserSOD (test); MAE: 0.049.

- [User Satisfaction Evaluation on User Study Shopping](<https://www.sota2.com/research/sota/user-satisfaction-evaluation-on-user-study-shopping.md>): User Satisfaction Evaluation; User Study Shopping; Average Satisfaction Score: 79.36.

- [User Satisfaction Evaluation on User Study Navigation](<https://www.sota2.com/research/sota/user-satisfaction-evaluation-on-user-study-navigation.md>): User Satisfaction Evaluation; User Study Navigation; Average Score: 85.07.

- [User Satisfaction Evaluation on User Study Industry](<https://www.sota2.com/research/sota/user-satisfaction-evaluation-on-user-study-industry.md>): User Satisfaction Evaluation; User Study Industry; Average Score: 55.01.

- [Salient Object Detection on ECSSD](<https://www.sota2.com/research/sota/salient-object-detection-on-ecssd.md>): Salient Object Detection; ECSSD; MAE: 0.021.

- [Salient Object Detection on HKU-IS](<https://www.sota2.com/research/sota/salient-object-detection-on-hku-is.md>): Salient Object Detection; HKU-IS; MAE: 0.021.

- [Salient Object Detection on PASCAL-S](<https://www.sota2.com/research/sota/salient-object-detection-on-pascal-s.md>): Salient Object Detection; PASCAL-S; MAE: 0.045.

- [Referring Image Segmentation on RefCOCO](<https://www.sota2.com/research/sota/referring-image-segmentation-on-refcoco.md>): Referring Image Segmentation; RefCOCO; cIoU: not recorded.

- [Referring Image Segmentation on RefCOCO+](<https://www.sota2.com/research/sota/referring-image-segmentation-on-refcoco-plus.md>): Referring Image Segmentation; RefCOCO+; cIoU: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.03526>)

[PDF](<https://arxiv.org/pdf/2604.03526.pdf>)
