Would Deep Generative Models Amplify Bias in Future Models?

4 April 2024

Papers citing "Would Deep Generative Models Amplify Bias in Future Models?"

8 / 8 papers shown

Title
FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing Jinya Sakurai Issei Sato 74 0 0 06 Feb 2025
Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World Joshua Kazdan Rylan Schaeffer Apratim Dey Matthias Gerstgrasser Rafael Rafailov D. Donoho Sanmi Koyejo 45 11 0 22 Oct 2024
Multimodal Composite Association Score: Measuring Gender Bias in Generative Multimodal Models Abhishek Mandal Susan Leavy Suzanne Little EGVM 26 18 0 26 Apr 2023
Social Biases through the Text-to-Image Generation Lens Ranjita Naik Besmira Nushi 91 113 0 30 Mar 2023
Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis Lukas Struppek Dominik Hintersdorf Felix Friedrich Manuel Brack P. Schramowski Kristian Kersting 66 26 0 19 Sep 2022
Data Feedback Loops: Model-driven Amplification of Dataset Biases Rohan Taori Tatsunori B. Hashimoto 64 42 0 08 Sep 2022
A Survey on Bias in Visual Datasets Simone Fabbrizzi Symeon Papadopoulos Eirini Ntoutsi Y. Kompatsiaris 119 119 0 16 Jul 2021
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts Soravit Changpinyo P. Sharma Nan Ding Radu Soricut VLM 273 1,077 0 17 Feb 2021