# Understanding Gender and Racial Disparities in Image Recognition Models

Source: [Understanding Gender and Racial Disparities in Image Recognition Models](<https://www.sota2.com/research/paper/68fa6a5d1e209131cea27ba4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:23:37.152Z

Authors: Rohan Mahadev, Anindya Chakravarti

Published: 2021-07-20T01:05:31.000Z

## Abstract

Large scale image classification models trained on top of popular datasets such as Imagenet have shown to have a distributional skew which leads to disparities in prediction accuracies across different subsections of population demographics. A lot of approaches have been made to solve for this distributional skew using methods that alter the model pre, post and during training. We investigate one such approach - which uses a multi-label softmax loss with cross-entropy as the loss function instead of a binary cross-entropy on a multi-label classification problem on the Inclusive Images dataset which is a subset of the OpenImages V6 dataset. We use the MR2 dataset, which contains images of people with self-identified gender and race attributes to evaluate the fairness in the model outcomes and try to interpret the mistakes by looking at model activations and suggest possible fixes.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2107.09211>)

[PDF](<https://arxiv.org/pdf/2107.09211.pdf>)