VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution

1 code implementation • NeurIPS 2023 • Siobhan Mackenzie Hall, Fernanda Gonçalves Abrantes, Hanwen Zhu, Grace Sodunke, Aleksandar Shtedritski, Hannah Rose Kirk

We introduce VisoGender, a novel dataset for benchmarking gender bias in vision-language models.

Benchmarking Retrieval

Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets

1 code implementation • 24 May 2023 • Brandon Smith, Miguel Farinha, Siobhan Mackenzie Hall, Hannah Rose Kirk, Aleksandar Shtedritski, Max Bain

To address this issue, we propose a novel dataset debiasing pipeline to augment the COCO dataset with synthetic, gender-balanced contrast sets, where only the gender of the subject is edited and the background is fixed.

A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning

1 code implementation • 22 Mar 2022 • Hugo Berg, Siobhan Mackenzie Hall, Yash Bhalgat, Wonsuk Yang, Hannah Rose Kirk, Aleksandar Shtedritski, Max Bain

Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation.