# Seeing Faces in Things: A Model and Dataset for Pareidolia

arXiv: https://arxiv.org/abs/2409.16143 · HTML: https://mlsanity.com/paper/2409.16143/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 67 references that are in the map.
- First posted on arXiv 24 Sep 2024.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [The VIA Annotation Software for Images, Audio and Video](https://mlsanity.com/paper/1904.10699/) (2019)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [S3FD: Single Shot Scale-invariant Face Detector](https://mlsanity.com/paper/1708.05237/) (2017)
- [DSFD: Dual Shot Face Detector](https://mlsanity.com/paper/1810.10220/) (2018)
- [Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysis](https://mlsanity.com/paper/1807.07814/) (2018)
- [PyramidBox: A Context-assisted Single Shot Face Detector](https://mlsanity.com/paper/1803.07737/) (2018)
- [Learning Aligned Cross-Modal Representations from Weakly Aligned Data](https://mlsanity.com/paper/1607.07295/) (2016)
- [AnimalWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces](https://mlsanity.com/paper/1909.04951/) (2019)
- [Detecting People in Artwork with CNNs](https://mlsanity.com/paper/1610.08871/) (2016)
- [Totally Looks Like - How Humans Compare, Compared to Machines](https://mlsanity.com/paper/1803.01485/) (2018)
- [The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs](https://mlsanity.com/paper/1505.00110/) (2015)
- [Detecting People in Cubist Art](https://mlsanity.com/paper/1409.6235/) (2014)
- [A Fast and Accurate Unconstrained Face Detector](https://mlsanity.com/paper/1408.1656/) (2014)

## Built on by (most cited first, 4 of 4)

- [Can Modern Vision Models Understand the Difference Between an Object and a Look-alike?](https://mlsanity.com/paper/2511.19200/) (2025)
- [When Visual Evidence is Ambiguous: Pareidolia as a Diagnostic Probe for Vision Models](https://mlsanity.com/paper/2603.03989/) (2026)
- [GenMatter: Perceiving Physical Objects with Generative Matter Models](https://mlsanity.com/paper/2604.22160/) (2026)
- [Diamonds in the Sky: Pareidolic Animals in Clouds](https://mlsanity.com/paper/2606.01361/) (2026)

## Abstract (arXiv)

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