December 03, 2019
We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to a multi-modal two-stream model, processing both visual and textual inputs in separate streams that interact through co-attentional transformer layers. We pretrain our model through two proxy tasks on the large, automatically collected Conceptual Captions dataset and then transfer it to multiple established vision-and-language tasks -- visual question answering, visual commonsense reasoning, referring expressions, and caption-based image retrieval -- by making only minor additions to the base architecture. We observe significant improvements across tasks compared to existing task-specific models -- achieving state-of-the-art on all four tasks. Our work represents a shift away from learning groundings between vision and language only as part of task training and towards treating visual grounding as a pretrainable and transferable capability.
Publisher
NeurIPS
July 23, 2024
Llama team
July 23, 2024
June 25, 2024
Min-Jae Hwang, Ilia Kulikov, Benjamin Peloquin, Hongyu Gong, Peng-Jen Chen, Ann Lee
June 25, 2024
June 05, 2024
Robin San Romin, Pierre Fernandez, Hady Elsahar, Alexandre Deffosez, Teddy Furon, Tuan Tran
June 05, 2024
May 24, 2024
May 24, 2024
Product experiences
Foundational models
Product experiences
Latest news
Foundational models