Lune

CVPR Findings2026

DebFilter: Eradicating Biases Stashed in Value

Seung Hyuk Lee, Songkuk Kim

问 Lune

摘要

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.

问 Lune

尽管问,回答会引用原文。

Lune 会读完全文和相关的 Paper,每个回答都附上所依据的原文段落。

可以从这些问题问起

Lune 的依据

全文 · 相关的 Paper

获取答案

免费开始,无需绑卡

它引用的 Paper16

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 47,906 次引用
  2. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 次引用
  3. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 13,123 次引用
  4. Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 11,724 次引用
  5. SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, Andreas Blattmann 等ICLR 2024 · 4,569 次引用

相关 Paper

  1. BiasFilter: An Inference-Time Debiasing Framework for Large Language ModelsXiaoqing Cheng, Ruizhe Chen, Hongying Zan, Yuxiang Jia 等EMNLP Findings 2025 · 1 次引用
  2. Finetuning Text-to-Image Diffusion Models for FairnessXudong Shen, Chao Du, Tianyu Pang, Min Lin 等ICLR 2024 · 97 次引用
  3. Fair Text-to-Image Diffusion via Fair MappingJia Li, Lijie Hu, Jingfeng Zhang, Tianhang Zheng 等AAAI 2025 · 36 次引用
  4. FairRAG: Fair Human Generation via Fair Retrieval AugmentationRobik Shrestha, Yang Zou, Qiuyu Chen, Zhiheng Li 等CVPR 2024 · 6 次引用
  5. Mitigating Social Biases in Text-to-Image Diffusion Models via Linguistic-Aligned Attention GuidanceYue Jiang, Yueming Lyu, Ziwen He, Bo Peng 等ACM MM 2024 · 4 次引用
黄昏的海面,两侧是细线勾勒的悬崖