研究人眼错觉看脸现象，建了五千张‘物中见脸’数据集。
Seeing Faces in Things: A Model and Dataset for Pareidolia
- 构建‘物中见脸’图像数据集，含人类标注的错觉人脸。
- 发现顶尖人脸检测模型误检率远高于人类，存在显著差距。
- 提出统计模型解释错觉成因，适合视觉认知与安全领域研究者。
人类视觉系统对各种形状和大小的脸部具有高度敏感性。这虽有助于在野外发现潜在威胁，但也导致对随机刺激产生虚假的脸部感知，即‘面庞错觉’（pareidolia）——在咖啡渍或云朵中看到人脸。本文从计算机视觉角度研究此现象，构建了一个名为‘物中见脸’（Faces in Things）的数据集，包含五千张来自网络的图像，并由人工标注出其中的错觉人脸。利用该数据集，我们评估了当前最先进的脸部检测器在错觉场景下的表现，发现其错误检出率显著高于人类，揭示了人机之间的重要行为差异。研究还表明，人类进化中对动物及人类脸部的快速识别需求可能部分解释了这一差异。最后，我们提出了一个简单的图像错觉统计模型，并通过人类实验和检测器测试验证了模型预测：特定图像条件下更易诱发错觉。数据集与网站：https://aka.ms/faces-in-things
原文摘要 · Abstract (English)
The human visual system is well-tuned to detect faces of all shapes and sizes. While this brings obvious survival advantages, such as a better chance of spotting unknown predators in the bush, it also leads to spurious face detections. ``Face pareidolia'' describes the perception of face-like structure among otherwise random stimuli: seeing faces in coffee stains or clouds in the sky. In this paper, we study face pareidolia from a computer vision perspective. We present an image dataset of ``Faces in Things'', consisting of five thousand web images with human-annotated pareidolic faces. Using this dataset, we examine the extent to which a state-of-the-art human face detector exhibits pareidolia, and find a significant behavioral gap between humans and machines. We find that the evolutionary need for humans to detect animal faces, as well as human faces, may explain some of this gap. Finally, we propose a simple statistical model of pareidolia in images. Through studies on human subjects and our pareidolic face detectors we confirm a key prediction of our model regarding what image conditions are most likely to induce pareidolia. Dataset and Website: https://aka.ms/faces-in-things
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。