GPTFace: Generative Pre-training of Facial-Linguistic Transformer by Span Masking and Weakly Correlated Text-image Data

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Yudong, Li, Hao, Hou, Xianxu, Shen, Linlin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908604473278464
author Li, Yudong
Li, Hao
Hou, Xianxu
Shen, Linlin
author_facet Li, Yudong
Li, Hao
Hou, Xianxu
Shen, Linlin
contents Compared to the prosperity of pre-training models in natural image understanding, the research on large-scale pre-training models for facial knowledge learning is still limited. Current approaches mainly rely on manually assembled and annotated face datasets for training, but labeling such datasets is labor-intensive and the trained models have limited scalability beyond the training data. To address these limitations, we present a generative pre-training model for facial knowledge learning that leverages large-scale web-built data for training. We use texts and images containing human faces crawled from the internet and conduct pre-training on self-supervised tasks, including masked image/language modeling (MILM) and image-text matching (ITM). During the generation stage, we further utilize the image-text matching loss to pull the generation distribution towards the control signal for controllable image/text generation. Experimental results demonstrate that our model achieves comparable performance to state-of-the-art pre-training models for various facial downstream tasks, such as attribution classification and expression recognition. Furthermore, our approach is also applicable to a wide range of face editing tasks, including face attribute editing, expression manipulation, mask removal, and photo inpainting.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18345
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GPTFace: Generative Pre-training of Facial-Linguistic Transformer by Span Masking and Weakly Correlated Text-image Data
Li, Yudong
Li, Hao
Hou, Xianxu
Shen, Linlin
Computer Vision and Pattern Recognition
Compared to the prosperity of pre-training models in natural image understanding, the research on large-scale pre-training models for facial knowledge learning is still limited. Current approaches mainly rely on manually assembled and annotated face datasets for training, but labeling such datasets is labor-intensive and the trained models have limited scalability beyond the training data. To address these limitations, we present a generative pre-training model for facial knowledge learning that leverages large-scale web-built data for training. We use texts and images containing human faces crawled from the internet and conduct pre-training on self-supervised tasks, including masked image/language modeling (MILM) and image-text matching (ITM). During the generation stage, we further utilize the image-text matching loss to pull the generation distribution towards the control signal for controllable image/text generation. Experimental results demonstrate that our model achieves comparable performance to state-of-the-art pre-training models for various facial downstream tasks, such as attribution classification and expression recognition. Furthermore, our approach is also applicable to a wide range of face editing tasks, including face attribute editing, expression manipulation, mask removal, and photo inpainting.
title GPTFace: Generative Pre-training of Facial-Linguistic Transformer by Span Masking and Weakly Correlated Text-image Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.18345