The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World
This project aims to serve as a foundation for vision-language artificial general intelligence research, addressing the problem of comprehensive visual understanding for AI systems.
The All-Seeing project tackled the challenge of panoptic visual recognition and understanding in the open world by creating a large-scale dataset (AS-1B) with over 1 billion annotated regions and developing a unified model (ASM) that achieves remarkable zero-shot performance on various vision-language tasks.
We present the All-Seeing (AS) project: a large-scale data and model for recognizing and understanding everything in the open world. Using a scalable data engine that incorporates human feedback and efficient models in the loop, we create a new dataset (AS-1B) with over 1 billion regions annotated with semantic tags, question-answering pairs, and detailed captions. It covers a wide range of 3.5 million common and rare concepts in the real world, and has 132.2 billion tokens that describe the concepts and their attributes. Leveraging this new dataset, we develop the All-Seeing model (ASM), a unified framework for panoptic visual recognition and understanding. The model is trained with open-ended language prompts and locations, which allows it to generalize to various vision and language tasks with remarkable zero-shot performance, including region-text retrieval, region recognition, captioning, and question-answering. We hope that this project can serve as a foundation for vision-language artificial general intelligence research. Models and the dataset shall be released at https://github.com/OpenGVLab/All-Seeing, and demo can be seen at https://huggingface.co/spaces/OpenGVLab/all-seeing.