跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 25 天前AI 評分36

SynthFaces:均衡的大規模人臉數據集

SynthFaces: Balanced Large Scale Human Dataset

AI 導讀

SynthFaces 以 Arc2Face 擴散模型結合身份嵌入向量上的 flow matching,生成具多元身份、標籤分佈均衡的合成人臉數據集,供生成模型訓練及微調。數據集中的圖像與身份均為合成,旨在減少對真實個人圖像的直接依賴,並以最近鄰非洩漏指標檢查身份分離。研究亦展示以該數據集微調現有的 adapter-based 個人化生成方法。

正文

Published on Oct 29

Authors:

,

,

Abstract

A pipeline combining Arc2Face diffusion with flow matching on identity embeddings generates a balanced synthetic face dataset to improve fairness and reduce privacy risks in generative model training.

The pursuit of fair and equitable AI in human-centric tasks is critically hindered by the inherent biases and privacy risks of real-world datasets, which offer imbalanced representations of identity and often contain sensitive personal information. Consequently, state-of-the-art generative models trained on this skewed data exhibit unfair performance, particularly in identity-preserving generation. In this work we propose a pipeline for controllable generation of dataset with diverse faces for generative models training and finetuning. We achieve this by expanding foundational Arc2Face diffusion model with a flow matching generative model in the manifold of identity embeddings. We demonstrate that such approach achieves both goals of generative fidelity and label diversity not present in real human-centric datasets. As a result we collect and further contextualize a highly balanced identity-centric dataset of humans named SynthFaces. By design, our released images and identities are synthetic, reducing direct reliance on real personal images; we empirically check identity separation with a nearest-neighbor non-leakage metric. We purpose it for training and tuning of fair models for various downstream tasks, and showcase its usability in finetuning an existing adapter-based method for personalized generation.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.40119

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

shredder67/id-flow

Updated 3 days ago

Datasets citing this paper 1

shredder67/synthfaces-faces-balanced

Preview •

Updated 1 day ago

•

30

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.40119 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co