Methods › Computer Vision › Vision and Language Pre-Trained Models › XGPT

XGPT

1 paper tagged archive 2025-07-28

Introduced by Qiaolin Xia et al. in XGPT: Cross-modal Generative Pre-Training for Image Captioning

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

XGPT is a method of cross-modal generative pre-training for image captioning designed to pre-train text-to-image caption generators through three novel generation tasks, including image-conditioned masked language modeling (IMLM), image-conditioned denoising autoencoding (IDA), and text-conditioned image feature generation (TIGF). The pre-trained XGPT can be fine-tuned without any task-specific architecture modifications and build strong image captioning models.

PaperSource

Papers archive 2025-07-28

1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

11 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Data Augmentation1
Denoising1
Image Captioning1
Image Retrieval1
Image-text Retrieval1
Language Modeling1
Language Modelling1
Masked Language Modeling1
Retrieval1
Text Retrieval1
Visual Question Answering (VQA)1

Usage over time archive 2025-07-28

Papers per year tagged with XGPT: 2020 to 2020, peak 1 1 0 2020: 1 paper 2020
Papers per year the archive tags with this method, by the paper's archive date (1 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Vision and Language Pre-Trained Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections