Visual Knowledge in the Big Model Era: Retrospect and Prospect
This is an incremental review paper that synthesizes existing ideas to guide future research in visual knowledge for AI, without presenting new experimental results.
The paper reviews the concept of visual knowledge as a representation for visual concepts and relations, tracing its origins and development, and highlights its potential role in advancing machine intelligence, particularly in the era of large AI models.
Visual knowledge is a new form of knowledge representation that can encapsulate visual concepts and their relations in a succinct, comprehensive, and interpretable manner, with a deep root in cognitive psychology. As the knowledge about the visual world has been identified as an indispensable component of human cognition and intelligence, visual knowledge is poised to have a pivotal role in establishing machine intelligence. With the recent advance of Artificial Intelligence (AI) techniques, large AI models (or foundation models) have emerged as a potent tool capable of extracting versatile patterns from broad data as implicit knowledge, and abstracting them into an outrageous amount of numeric parameters. To pave the way for creating visual knowledge empowered AI machines in this coming wave, we present a timely review that investigates the origins and development of visual knowledge in the pre-big model era, and accentuates the opportunities and unique role of visual knowledge in the big model era.