Grounded Language-Image Pre-training

TL;DR

GLIP is a grounded language-image pre-training model that unifies object detection and phrase grounding, leveraging large-scale data to learn semantic-rich visual representations with strong zero-shot and few-shot transfer capabilities.

Contribution

The paper introduces GLIP, a novel model that combines object detection and phrase grounding for pre-training, enabling effective learning from both detection and grounding data.

Findings

GLIP achieves 49.8 AP on COCO without seeing COCO images during pre-training.

GLIP surpasses state-of-the-art on COCO and LVIS after fine-tuning.

GLIP performs competitively on 13 downstream object detection tasks.

Abstract

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 27M grounding data, including 3M human-annotated and 24M web-crawled image-text pairs. The learned representations demonstrate strong zero-shot and few-shot transferability to various object-level recognition tasks. 1) When directly evaluated on COCO and LVIS (without seeing any images in COCO during pre-training), GLIP achieves 49.8 AP and 26.9 AP, respectively, surpassing many supervised baselines. 2) After fine-tuned on COCO, GLIP achieves 60.8 AP on val and 61.5 AP on test-dev, surpassing prior SoTA. 3) When transferred to 13 downstream object detection tasks, a 1-shot GLIP rivals with a fully-supervised Dynamic Head. Code is released at https://github.com/microsoft/GLIP.