Saved in:
Bibliographic Details
Main Authors: Olmos, Carolina Lopez, Neophytou, Alexandros, Sengupta, Sunando, Papadopoulos, Dim P.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.06352
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929380418125824
author Olmos, Carolina Lopez
Neophytou, Alexandros
Sengupta, Sunando
Papadopoulos, Dim P.
author_facet Olmos, Carolina Lopez
Neophytou, Alexandros
Sengupta, Sunando
Papadopoulos, Dim P.
contents Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for training pose challenges in ensuring the responsible development of these models, and mitigation through hard prompting or embedding alteration, are the most common present solutions. Our work introduces a novel approach to achieve diverse and inclusive synthetic images by learning a direction in the latent space and solely modifying the initial Gaussian noise provided for the diffusion process. Maintaining a neutral prompt and untouched embeddings, this approach successfully adapts to diverse debiasing scenarios, such as geographical biases. Moreover, our work proves it is possible to linearly combine these learned latent directions to introduce new mitigations, and if desired, integrate it with text embedding adjustments. Furthermore, text-to-image models lack transparency for assessing bias in outputs, unless visually inspected. Thus, we provide a tool to empower developers to select their desired concepts to mitigate. The project page with code is available online.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06352
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Latent Directions: A Simple Pathway to Bias Mitigation in Generative AI
Olmos, Carolina Lopez
Neophytou, Alexandros
Sengupta, Sunando
Papadopoulos, Dim P.
Computer Vision and Pattern Recognition
Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for training pose challenges in ensuring the responsible development of these models, and mitigation through hard prompting or embedding alteration, are the most common present solutions. Our work introduces a novel approach to achieve diverse and inclusive synthetic images by learning a direction in the latent space and solely modifying the initial Gaussian noise provided for the diffusion process. Maintaining a neutral prompt and untouched embeddings, this approach successfully adapts to diverse debiasing scenarios, such as geographical biases. Moreover, our work proves it is possible to linearly combine these learned latent directions to introduce new mitigations, and if desired, integrate it with text embedding adjustments. Furthermore, text-to-image models lack transparency for assessing bias in outputs, unless visually inspected. Thus, we provide a tool to empower developers to select their desired concepts to mitigate. The project page with code is available online.
title Latent Directions: A Simple Pathway to Bias Mitigation in Generative AI
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.06352