Salesforce - Blip Image Captioning

Vision-Language Pre-training (VLP) has advanced the performance of 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 that 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.

The model is great for image-to-text flows. It has a single configuration. You can get the captioning or ask questions to the image.

@misc{https://doi.org/10.48550/arxiv.2201.12086,
 doi = {10.48550/ARXIV.2201.12086},
 
 url = {https://arxiv.org/abs/2201.12086},
 
 author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
 
 keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
 
 title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
 
 publisher = {arXiv},
 
 year = {2022},
 
 copyright = {Creative Commons Attribution 4.0 International}
}