arXiv Computer Vision
Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Oct 3
Debias Anything: Fairness with Diversity without Supervision in Diffusion Models
The paper introduces a method called Debias Anything that jointly addresses fairness and diversity in diffusion models without requiring sensitive-attribute annotations. By connecting a frozen diffusion model to a pretrained vision-language embedding space via an adapter, the approach uses pairs of text prompts to guide batch composition toward desired attribute proportions and employs a disagreement score to promote diversity. The method is applicable to both unconditional and text-conditional diffusion models and demonstrates improved quality and diversity while maintaining comparable fairness levels in experiments.
arXiv Computer Vision
Sep 10
Efficient Fairness Auditing Across Guidance Scales in Text-to-Image Diffusion Models via Causal Abstraction
arXiv:2609.09486v1 Announce Type: cross Abstract: Fairness auditing of text-to-image diffusion models often requires generating large numbers of images across sampling configurations, making comprehe...
arXiv Machine Learning
Jun 2
KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation
arXiv:2606. 01282v1 Announce Type: cross Abstract: Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cultural stereotypes they inherit from training data (rendering women, people of colour, older adults, and non-Western cultures as under-represented or caricatured) become a population-level harm at deployment scale.
arXiv Machine Learning
Jun 9
Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
arXiv:2512. 08724v3 Announce Type: replace Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age.
arXiv Machine Learning
Aug 27
Fairness-Aware Test-Time Prompt Tuning
The paper introduces FairTPT, a fairness-aware test‑time prompt tuning method for vision‑language models like CLIP. It jointly minimizes target marginal entropy while maximizing spurious marginal entropy to reduce bias under subpopulation shifts. Experiments show that standard episodic test‑time adaptation can worsen disparities, but FairTPT outperforms existing debiasing methods while preserving overall performance.
arXiv AI
Jul 24
Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.