Methods › Computer Vision › Vision and Language Pre-Trained Models › Unified VLP
Unified VLP
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Unified VLP is unified encoder-decoder model for general vision-language pre-training. The models uses a shared multi-layer transformers network for both encoding and decoding. The model is pre-trained on large amount of image-text pairs using the unsupervised learning objectives of two tasks: bidirectional and sequence-to-sequence (seq2seq) masked vision-language prediction. Model architecture for pre-training. For pre-training , the input comprises of image input, sentence input, and three special tokens ([CLS], [SEP], [STOP]). The image is processed as N Region of Interests (RoIs) and region features are extracted. The sentence is tokenized and masked with [MASK] tokens for the later masked language modeling task. The model consists of 12 layers of Transformer blocks, each having a masked self-attention layer and feed-forward module, where the self-attention mask controls what input context the prediction conditions on. Two self-attention masks are implemented depending on whether the objective is bidirectional or seq2seq. The model is fine-tuned for image captioning and visual question answering.
Papers archive 2025-07-28
2 shown of 2, 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.
-
MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations 2 Mar 2025 · 0 repositories · arXiv:2503.01019
-
Unified Vision-Language Pre-Training for Image Captioning and VQA 24 Sep 2019 · 3 repositories · arXiv:1909.11059Syntology ran 5 of 14 samples · 9 unverified · 13 pointer-only (licence)
Tasks archive 2025-07-28
16 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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