MIST: Mitigating Intersectional Bias with Disentangled Cross-Attention Editing in Text-to-Image Diffusion Models

28 March 2024

Papers citing "MIST: Mitigating Intersectional Bias with Disentangled Cross-Attention Editing in Text-to-Image Diffusion Models"

6 / 6 papers shown

Title
Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis Taihang Hu Linxuan Li Joost van de Weijer Hongcheng Gao Fahad Shahbaz Khan Jian Yang Ming-Ming Cheng Kai Wang Yaxing Wang DiffM 39 4 0 11 Nov 2024
Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions S. A. Baumann Felix Krause Michael Neumayr Nick Stracke Vincent Tao Hu Bjorn Ommer Björn Ommer DiffM LM&Ro 63 11 0 25 Mar 2024
Improving Fairness using Vision-Language Driven Image Augmentation Moreno DÍncà Christos Tzelepis Ioannis Patras N. Sebe 30 12 0 02 Nov 2023
Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens Saad Hassan Matt Huenerfauth Cecilia Ovesdotter Alm 36 38 0 01 Oct 2021
Evaluating Debiasing Techniques for Intersectional Biases Shivashankar Subramanian Xudong Han Timothy Baldwin Trevor Cohn Lea Frermann 77 43 0 21 Sep 2021
U-Net: Convolutional Networks for Biomedical Image Segmentation Olaf Ronneberger Philipp Fischer Thomas Brox SSeg 3DV 229 74,467 0 18 May 2015