activity
20202026
most citedDivide and not forget: Ensemble of selectively trained experts in Continual Learning

11 citations · 18 across the 13 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2024

Exploring the Stability Gap in Continual Learning: The Role of the Classification Head

Wojciech Łapacz, Daniel Marczak, Filip Szatkowski +1

Continual learning (CL) has emerged as a critical area in machine learning, enabling neural networks to learn from evolving data distributions while mitigating catastrophic forgett…

cs.LG2024★ 1 cited

Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning

Grzegorz Rypeść, Sebastian Cygert, Tomasz Trzciński +1

Exemplar-Free Class Incremental Learning (EFCIL) tackles the problem of training a model on a sequence of tasks without access to past data. Existing state-of-the-art methods repre…

cs.LG2024★ 1 cited

MagMax: Leveraging Model Merging for Seamless Continual Learning

Daniel Marczak, Bartłomiej Twardowski, Tomasz Trzciński +1

This paper introduces a continual learning approach named MagMax, which utilizes model merging to enable large pre-trained models to continuously learn from new data without forget…

cs.LG2024

Realistic Evaluation of Test-Time Adaptation Algorithms: Unsupervised Hyperparameter Selection

Sebastian Cygert, Damian Sójka, Tomasz Trzciński +1

Test-Time Adaptation (TTA) has recently emerged as a promising strategy for tackling the problem of machine learning model robustness under distribution shifts by adapting the mode…

cs.LG2024

Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers

Filip Szatkowski, Yaoyue Zheng, Fei Yang +3

Continual learning is crucial for applying machine learning in challenging, dynamic, and often resource-constrained environments. However, catastrophic forgetting - overwriting pre…

cs.LG2024★ 1 cited

GUIDE: Guidance-based Incremental Learning with Diffusion Models

Bartosz Cywiński, Kamil Deja, Tomasz Trzciński +2

We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten. Existing generative strategies combat catastro…