BLIP: Bootstrapping Language Image Pre training for Unified Vision Language Understanding and Generation Model card for BLIP trained on image text matching large architecture (with ViT large backbone) trained on COCO dataset. : : Pull figure from BLIP official repo Image source: https://github.com/salesforce/BLIP TL;DR Authors from the paper write in the abstract: Vision Language Pre training (VLP) has advanced the performance for many vision language tasks. However, most existing pre trained models only excel in either understanding based tasks or generation based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the captions, where a captioner generates synthetic captions and a filter removes the noisy ones. We achieve state of the art results on a wide range of vision language tasks, such as image text retrieval (+2.7% in average recall@1), im…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy