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
April 14, 2024
Heng-Jui Chang, Ning Dong (AI), Ruslan Mavlyutov, Sravya Popuri, Andy Chung
April 14, 2024
March 05, 2024
Alex Liu, Matt Le, Apoorv Vyas, Bowen Shi, Andros Tjandra, Wei-Ning Hsu
March 05, 2024
December 11, 2023
Wei-Ning Hsu, Akinniyi Akinyemi, Alice Rakotoarison, Andros Tjandra, Apoorv Vyas, Baishan Guo, Bapi Akula, Bowen Shi, Brian Ellis, Ivan Cruz, Jeff Wang, Jiemin Zhang, Mary Williamson, Matt Le, Rashel Moritz, Robbie Adkins, William Ngan, Xinyue Zhang, Yael Yungster, Yi-Chiao Wu
December 11, 2023
November 30, 2023
Xutai Ma, Anna Sun, Siqi Ouyang, Hirofumi Inaguma, Paden Tomasello
November 30, 2023
Product experiences
Foundational models
Product experiences
Latest news
Foundational models