BLIP: LLM for vision-language tasks

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. BLIP is 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. BLIP 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 videolanguage tasks in a zero-shot manner.

In this video, I will talk about the following: What is the BLIP model architecture? What is CapFilt in BLIP, and how does it work? How does BLIP perform?

For more details, please look at https://arxiv.org/pdf/2201.12086.pdf and https://github.com/salesforce/BLIP

Li, Junnan, Dongxu Li, Caiming Xiong, and Steven Hoi. "BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation." In International Conference on Machine Learning, pp. 12888-12900. PMLR, 2022.