Join research seminar which will take place on June 22 at 2 pm CET on Zoom. Dr. Joost van de Weijer (Computer Vision Center, Barcelona) will conduct the lecture “Towards Label-Efficient and Multi-Agent Continual Learning”. For your convenience, there is also a possibility to use the IDEAS Conference Room.
Dr. Joost van de Weijer works as a Senior Scientist at the Computer Vision Center in Barcelona. He heads the Learning and Machine Perception (LAMP) research group. In his speech, he will discuss the transition from supervised continuous learning to unsupervised (and self-supervised) methods in continuous learning and multi-agent systems in the context of continuous learning.
To join the seminar, please use this link:
If you want to join our seminar at IDEAS NCBR Conference Room, please register at firstname.lastname@example.org
Title: „Towards Label-Efficient and Multi-Agent Continual Learning”
Abstract: Continual learning aims to accumulate knowledge from a stream of incoming data. The first part of this talk will focus on how we can move from supervised continual learning towards unsupervised (and self-supervised) methods for continual learning. The majority of continual learning literature focuses on supervised continual learning, where a learner adapts to a stream of fully labeled data while consolidating previously learned knowledge. Results for domain incremental and class incremental learning will be discussed. In the second part of the talk, the focus will be on multi-agent systems for continual learning. Instead of a single agent which learns on a stream of incoming data, systems of two agents will be considered. This allows agents to specialize in certain tasks without requiring them to consolidate knowledge from previous tasks. This technique is found to be beneficial in supervised, self-supervised, and other applications like incremental semantic segmentation. The results confirm that multi-agent continual learning allows for a good trade-off between plasticity and stability.