Timezone: »

 
Poster
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Junnan Li · DONGXU LI · Caiming Xiong · Steven Hoi

Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #212
in Poster Session 2 »

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), image captioning (+2.8% in CIDEr), and VQA (+1.6% in VQA score). BLIP also demonstrates strong generalization ability when directly transferred to video-language tasks in a zero-shot manner. Code and models are available at https://github.com/salesforce/BLIP.

Keywords: APP: Computer Vision · DL: Other Representation Learning

Author Information

Junnan Li (Salesforce)
DONGXU LI (Salesforce)
Caiming Xiong (Salesforce)
Steven Hoi (Salesforce)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors