CVPR Findings2026
DebFilter: Eradicating Biases Stashed in Value
Seung Hyuk Lee, Songkuk Kim
Abstract
original + gender & age filter + gender filter + age filter * Corresponding author
tations. This adjustment reconfigures the score landscape to produce balanced outputs while maintaining alignment with the intended text semantics. Unlike prior approaches that rely on fine-tuning or retraining, DebFilter operates entirely at inference time, requiring no additional data or model updates. Our results demonstrate that this method effectively mitigates social biases in generated images, offering an efficient and scalable pathway toward fairer and more inclusive text-to-image generation.
Ask Lune
Ask anything. The answer quotes the paper.
Lune reads all of it and the papers around it, then shows you the passages behind every answer.
Builds on16
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 11,724 citations
- SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, Andreas Blattmann et al.ICLR 2024 · 4,569 citations
Related papers
- BiasFilter: An Inference-Time Debiasing Framework for Large Language ModelsXiaoqing Cheng, Ruizhe Chen, Hongying Zan, Yuxiang Jia et al.EMNLP Findings 2025 · 1 citation
- Finetuning Text-to-Image Diffusion Models for FairnessXudong Shen, Chao Du, Tianyu Pang, Min Lin et al.ICLR 2024 · 97 citations
- Fair Text-to-Image Diffusion via Fair MappingJia Li, Lijie Hu, Jingfeng Zhang, Tianhang Zheng et al.AAAI 2025 · 36 citations
- FairRAG: Fair Human Generation via Fair Retrieval AugmentationRobik Shrestha, Yang Zou, Qiuyu Chen, Zhiheng Li et al.CVPR 2024 · 6 citations
- Mitigating Social Biases in Text-to-Image Diffusion Models via Linguistic-Aligned Attention GuidanceYue Jiang, Yueming Lyu, Ziwen He, Bo Peng et al.ACM MM 2024 · 4 citations
