# Revisiting Salient Object Detection from an Observer-Centric Perspective

arXiv: https://arxiv.org/abs/2602.06369 · HTML: https://mlsanity.com/paper/2602.06369/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 29 of 29)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [GRES: Generalized Referring Expression Segmentation](https://mlsanity.com/paper/2306.00968/) (2023)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Visual Saliency Based on Multiscale Deep Features](https://mlsanity.com/paper/1503.08663/) (2015)
- [Visual Saliency Transformer](https://mlsanity.com/paper/2104.12099/) (2021)
- [PACO: Parts and Attributes of Common Objects](https://mlsanity.com/paper/2301.01795/) (2023)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Highly Efficient Salient Object Detection with 100K Parameters](https://mlsanity.com/paper/2003.05643/) (2020)
- [VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning](https://mlsanity.com/paper/2311.15011/) (2023)
- [LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning](https://mlsanity.com/paper/2404.08767/) (2024)
- [EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding](https://mlsanity.com/paper/2309.08816/) (2023)
- [Instance-Level Salient Object Segmentation](https://mlsanity.com/paper/1704.03604/) (2017)
- [Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detection](https://mlsanity.com/paper/2408.04326/) (2024)
- [MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation](https://mlsanity.com/paper/2503.13881/) (2025)
- [SelfReformer: Self-Refined Network with Transformer for Salient Object Detection](https://mlsanity.com/paper/2205.11283/) (2022)
- [Realistic Saliency Guided Image Enhancement](https://mlsanity.com/paper/2306.06092/) (2023)
- [Salient Object Subitizing](https://mlsanity.com/paper/1607.07525/) (2016)
- [FOCUS: Towards Universal Foreground Segmentation](https://mlsanity.com/paper/2501.05238/) (2025)
- [What is a salient object? A dataset and a baseline model for salient object detection](https://mlsanity.com/paper/1412.5027/) (2014)
- [Salient Object Ranking with Position-Preserved Attention](https://mlsanity.com/paper/2106.05047/) (2021)
- [SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving](https://mlsanity.com/paper/2305.06940/) (2023)
- [Pluralistic Salient Object Detection](https://mlsanity.com/paper/2409.02368/) (2024)

## Abstract (arXiv)

Salient object detection is inherently a subjective problem, as observers with different priors may perceive different objects as salient. However, existing methods predominantly formulate it as an objective prediction task with a single groundtruth segmentation map for each image, which renders the problem under-determined and fundamentally ill-posed. To address this issue, we propose Observer-Centric Salient Object Detection (OC-SOD), where salient regions are predicted by considering not only the visual cues but also the observer-specific factors such as their preferences or intents. As a result, this formulation captures the intrinsic ambiguity and diversity of human perception, enabling personalized and context-aware saliency prediction. By leveraging multi-modal large language models, we develop an efficient data annotation pipeline and construct the first OC-SOD dataset named OC-SODBench, comprising 33k training, validation and test images with 152k textual prompts and object pairs. Built upon this new dataset, we further design OC-SODAgent, an agentic baseline which performs OC-SOD via a human-like "Perceive-Reflect-Adjust" process. Extensive experiments on our proposed OC-SODBench have justified the effectiveness of our contribution. Through this observer-centric perspective, we aim to bridge the gap between human perception and computational modeling, offering a more realistic and flexible understanding of what makes an object truly "salient." Code and dataset are publicly available at: https://github.com/Dustzx/OC_SOD