Continual Learning:
Fundamentals and Advances

DAI 2023 Workshop on Continual Learning: Fundamentals and Advances

To deal with the dynamic changes of the real world, incorporating new knowledge into existing models to adapt to new problems is a fundamental challenge of computer vision. Humans and animals need to incrementally absorb new experiences in order to survive in new environments, and evolution endows the entire lifetime system with stronger adaptability.With the advancement of foundation models, there is a growing interest in enhancing their capabilities through continual learning. This technology allows models to continually update their generalization abilities based on real-time data, thereby enhancing their robustness and functionality. Consequently, continual learning has emerged as a pivotal paradigm in machine learning, leveraging the continuous refinement of foundation models through fine-tuning.

The growing and widespread interest in this direction demonstrates its relevance and complexity. Our workshop aims to provide a venue where academic researchers and industry practitioners can come together to discuss the principles, limitations and applications of foundation models in continual learning, and promote the understanding of foundation models in continual learning, innovative algorithms, research on new technologies and applications.

There are two encouraged types of invited talks and peer reviewed oral research talks: (1) the academic talk on fundamental research on continual learning with an attempt of application on foundation models; (2) the industrial talk on practice of designing or applying continual learning techniques for real-world foundation model fine-tuning tasks.Each talk is expected to be presented as a lecture with slides.There will be a QA session at the end of each talk.

The Workshop will be a half-day event (13:30 pm to 17:00 pm).