Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation
Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024, 20024
This paper is about our proposed online continual learning algorithm MOSE, which is inspired by the multi-level feature extraction and cross-layer communication inherent to animal neural circuits, aiming to enhance the model's adaptivity to dynamic distributions and resistance against forgetting.
Recommended citation: Hongwei Yan, Liyuan Wang*, Kaisheng Ma*, and Yi Zhong*. "Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation." IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024. 1(1). https://arxiv.org/pdf/2404.00417