Related papers: DeAR: Debiasing Vision-Language Models with Additive Residuals

DeAR: Debiasing Vision-Language Models with Additive Residuals

URL: http://arxiv.org/abs/2303.10431v1
Date: Sat, 18 Mar 2023 14:57:43 GMT
Title: DeAR: Debiasing Vision-Language Models with Additive Residuals
Authors: Ashish Seth, Mayur Hemani, Chirag Agarwal
Abstract summary: Large pre-trained vision-language models (VLMs) provide rich, adaptable image and text representations. These models suffer from societal biases owing to the skewed distribution of various identity groups in the training data. We present DeAR, a novel debiasing method that learns additive residual image representations to offset the original representations.
Score: 5.672132510411465
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Large pre-trained vision-language models (VLMs) reduce the time for developing predictive models for various vision-grounded language downstream tasks by providing rich, adaptable image and text representations. However, these models suffer from societal biases owing to the skewed distribution of various identity groups in the training data. These biases manifest as the skewed similarity between the representations for specific text concepts and images of people of different identity groups and, therefore, limit the usefulness of such models in real-world high-stakes applications. In this work, we present DeAR (Debiasing with Additive Residuals), a novel debiasing method that learns additive residual image representations to offset the original representations, ensuring fair output representations. In doing so, it reduces the ability of the representations to distinguish between the different identity groups. Further, we observe that the current fairness tests are performed on limited face image datasets that fail to indicate why a specific text concept should/should not apply to them. To bridge this gap and better evaluate DeAR, we introduce the Protected Attribute Tag Association (PATA) dataset - a new context-based bias benchmarking dataset for evaluating the fairness of large pre-trained VLMs. Additionally, PATA provides visual context for a diverse human population in different scenarios with both positive and negative connotations. Experimental results for fairness and zero-shot performance preservation using multiple datasets demonstrate the efficacy of our framework.