Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency

TL;DR

This paper analyzes Twitter's AI image cropping fairness issues, revealing systemic disparities and argmax bias, and advocates for user agency and combined qualitative-quantitative approaches to mitigate representational harm.

Contribution

It critically evaluates fairness metrics in AI cropping, identifies biases, and proposes a shift towards user-centered design to address representational harms.

Findings

Systematic disparities in cropping based on skin tone and gender.

Argmax bias amplifies fairness issues in saliency-based cropping.

Formal fairness metrics alone are insufficient to prevent representational harm.

Abstract

Twitter uses machine learning to crop images, where crops are centered around the part predicted to be the most salient. In fall 2020, Twitter users raised concerns that the automated image cropping system on Twitter favored light-skinned over dark-skinned individuals, as well as concerns that the system favored cropping woman's bodies instead of their heads. In order to address these concerns, we conduct an extensive analysis using formalized group fairness metrics. We find systematic disparities in cropping and identify contributing factors, including the fact that the cropping based on the single most salient point can amplify the disparities because of an effect we term argmax bias. However, we demonstrate that formalized fairness metrics and quantitative analysis on their own are insufficient for capturing the risk of representational harm in automatic cropping. We suggest the removal of saliency-based cropping in favor of a solution that better preserves user agency. For developing a new solution that sufficiently address concerns related to representational harm, our critique motivates a combination of quantitative and qualitative methods that include human-centered design.