CVAIOct 24, 2024

FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation

arXiv:2410.18615v17 citationsh-index: 15NIPS
Originality Incremental advance
AI Analysis

This addresses quality degradation in fair text-to-image generation for users of generative AI, though it's an incremental improvement over existing prompt learning approaches.

The paper tackles the problem of degraded image quality in prompt learning for fair text-to-image generation, revealing that existing methods distort prompts and cause abnormalities in early denoising steps. The proposed FairQueue method improves generation quality by 15-20% on FID scores while maintaining competitive fairness across sensitive attributes.

Recently, prompt learning has emerged as the state-of-the-art (SOTA) for fair text-to-image (T2I) generation. Specifically, this approach leverages readily available reference images to learn inclusive prompts for each target Sensitive Attribute (tSA), allowing for fair image generation. In this work, we first reveal that this prompt learning-based approach results in degraded sample quality. Our analysis shows that the approach's training objective -- which aims to align the embedding differences of learned prompts and reference images -- could be sub-optimal, resulting in distortion of the learned prompts and degraded generated images. To further substantiate this claim, as our major contribution, we deep dive into the denoising subnetwork of the T2I model to track down the effect of these learned prompts by analyzing the cross-attention maps. In our analysis, we propose a novel prompt switching analysis: I2H and H2I. Furthermore, we propose new quantitative characterization of cross-attention maps. Our analysis reveals abnormalities in the early denoising steps, perpetuating improper global structure that results in degradation in the generated samples. Building on insights from our analysis, we propose two ideas: (i) Prompt Queuing and (ii) Attention Amplification to address the quality issue. Extensive experimental results on a wide range of tSAs show that our proposed method outperforms SOTA approach's image generation quality, while achieving competitive fairness. More resources at FairQueue Project site: https://sutd-visual-computing-group.github.io/FairQueue

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes