BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. (arXiv:2201.12086v1 [cs.CV])

Web: http://arxiv.org/abs/2201.12086

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 …

arxiv bootstrapping cv language training vision