从观察者视角重新定义显著性检测，让模型理解不同人的注意力差异。
Revisiting Salient Object Detection from an Observer-Centric Perspective
- 引入观察者因素（偏好、意图）建模主观显著性
- 构建含152k文本提示的OC-SODBench数据集
- 设计类人推理流程的OC-SODAgent，适合个性化视觉任务
显著性检测本质上是主观问题，不同观察者因先验不同可能认为不同物体显著。现有方法多将其视为客观预测任务，每张图仅有一个标注真值，导致问题欠定且根本上病态。为此，我们提出观察者中心显著性检测（OC-SOD），在预测时不仅考虑视觉线索，还融合观察者的特定因素（如偏好或意图），从而捕捉人类感知的内在模糊性与多样性，实现个性化、上下文感知的显著性预测。通过多模态大语言模型，我们构建了首个OC-SOD数据集OC-SODBench，包含33,000张训练、验证与测试图像，以及152,000条文本提示和对象对。基于此数据集，我们设计了OC-SODAgent这一代理基线，通过类人“感知-反思-调整”过程完成检测。在所提数据集上的大量实验验证了方法的有效性。该视角旨在弥合人类感知与计算建模之间的差距，提供更真实、灵活的‘显著性’理解。代码与数据集已公开：https://github.com/Dustzx/OC_SOD
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。