arXiv cs.CY· Elena Sirotkina·· 12 小时前AI 评分59
人类视觉与计算机视觉对比：显著性模型对年龄、种族和收入群体存在系统性偏差
Human versus Computer Vision
AI 导读
Elena Sirotkina 在 arXiv 发表研究，用八个公开眼动数据集共 27,384 名参与者（含 2,993 名美国成年人的 1,140 万个网络摄像头注视点）评估主流计算机视觉显著性模型。
正文
Abstract:Computer vision saliency models predict where people will look, one map per image, and a predicted-attention industry sells those maps in place of measuring real viewers. I evaluate the leading models against every publicly available eye-tracking corpus that records viewer demographics, comprising 27,384 participants across eight datasets, including 11.4 million webcam gaze points from 2,993 US adults recruited to national quotas while viewing circulating news images. I show that a single map predicts where every group looks about equally well, but systematically ignores how long each place holds a group's attention. That time follows a clear sociodemographic and political fingerprint, so the map carries a systematic bias against the youngest and oldest viewers and against Black, lower-income, and Republican-leaning ones. I use each group's own gaze to test whether it carries a learnable pattern, across every demographic axis the sample supports. Showing which audiences these systems can learn and what determines this sets the standard for judging claims that computer vision captures diverse human vision.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY) |
| Cite as: | arXiv:2608.10181 [cs.CV] |
| (or arXiv:2608.10181v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2608.10181 arXiv-issued DOI via DataCite |
Submission history
From: Elena Sirotkina [view email]
[v1]
Mon, 10 Aug 2026 19:53:24 UTC (5,182 KB)
[v2]
Sat, 24 Oct 2026 03:04:34 UTC (2,076 KB)
来源：arXiv cs.CY · arxiv.org