Grounded Language-Image Pre-training. (arXiv:2112.03857v2 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/2112.03857

This paper presents a grounded language-image pre-training (GLIP) model for
learning object-level, language-aware, and semantic-rich visual
representations. GLIP unifies object detection and phrase grounding for
pre-training. The unification brings two benefits: 1) it allows GLIP to learn
from both detection and grounding data to improve both tasks and bootstrap a
good grounding model; 2) GLIP can leverage massive image-text pairs by
generating grounding boxes in a self-training fashion, making the learned
representation semantic-rich. In our experiments, we pre-train GLIP on …

arxiv cv image language pre-training training