{"ID":2852082,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.18345","arxiv_id":"2510.18345","title":"GPTFace: Generative Pre-training of Facial-Linguistic Transformer by Span Masking and Weakly Correlated Text-image Data","abstract":"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.","short_abstract":"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 a...","url_abs":"https://arxiv.org/abs/2510.18345","url_pdf":"https://arxiv.org/pdf/2510.18345v1","authors":"[\"Yudong Li\",\"Hao Li\",\"Xianxu Hou\",\"Linlin Shen\"]","published":"2025-10-21T06:55:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\",\"Language Model\"]","has_code":false}