Grounded Language-Image Pre-training
Grounded Language-Image Pre-trainingLiunian Harold Li 1 , Pengchuan Zhang 2 , Haotian Zhang 3 , Jianwei Yang2, Chunyuan Li2, Yiwu Zhong4 ,Lijuan Wang5, Lu Yuan5, Lei Zhang6, Jenq-Neng Hwang3, Kai-Wei Chang1, Jianfeng Gao21UCLA,2Microsoft Research,3University of Washington,4University of Wisconsin-Madison,5Microsoft Cloud and AI,6International Digital Economy paper presents a Grounded Language-Image Pre-training (GLIP) model for learningobject-level, language -aware, andsemantic-richvisual representations. GLIP uni-fies object detection and phrase grounding for unification brings two benefits: 1) it allows GLIPto learn from both detection and grounding data to im-prove both tasks and bootstrap a good grounding model;2) GLIP can leverage massive image-text pairs by generat-ing grounding boxes in a self-training fashion, ma
(GLIP-L) on 27M grounding data, including 3M human-annotated fine-grained data and 24M web-crawled image-text pairs. For the 24M image-text pairs, there are 78.1M high-confidence (> 0:5) phrase-box pseudo annotations, with 58.4M unique noun phrases. We showcase two real examples of the generated boxes in Figure2. The teacher
Download Grounded Language-Image Pre-training
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: