1 code implementation • 5 Mar 2024 • Haneol Kang, Dong-Wan Choi
The stability-plasticity dilemma is a major challenge in continual learning, as it involves balancing the conflicting objectives of maintaining performance on previous tasks while learning new tasks.
1 code implementation • 18 Feb 2024 • Hyunjune Shin, Dong-Wan Choi
In this paper, we propose the teacher-agnostic data-free knowledge distillation (TA-DFKD) method, with the goal of more robust and stable performance regardless of teacher models.
1 code implementation • 29 Nov 2022 • Seong-Woong Kim, Dong-Wan Choi
In this paper, we overcome this limitation by proposing a simple yet effective normalization method that can effectively control both mean and variance of the weight distribution of novel classes without using any base samples and thereby achieve a satisfactory performance on both novel and base classes.
Ranked #1 on Generalized Few-Shot Learning on CUB
2 code implementations • 3 Jul 2021 • Hakbin Kim, Dong-Wan Choi
In spite of the great success of deep learning technologies, training and delivery of a practically serviceable model is still a highly time-consuming process.
1 code implementation • 3 Jul 2021 • Jong-Yeong Kim, Dong-Wan Choi
Continual learning has been a major problem in the deep learning community, where the main challenge is how to effectively learn a series of newly arriving tasks without forgetting the knowledge of previous tasks.
Ranked #1 on Class Incremental Learning on cifar100