Foundational Models for Continual Learning: An Empirical Study of Latent Replay

2022

19 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Large Language Models, Meta & Continual Learning

Citations in the corpus

• A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “In particular, the benefits for downstream continual learning tend to be more apparent when pre-training with larger data size [89], [197], larger model size [89] and contrastive loss [188], [190].”
• Scaling the Number of Tasks in Continual Learning (2022, methodology): “In this section we study how Setting: To this end 1000 downstream tasks are samples from either out-of-distribution (OOD) datasets, i.e. Cars196 Krause et al. [2013] and FGCVAicraft [Maji et al., 2013], or in-distribution (ID) dataset CIFAR100 as in Ostapenko et al. [2022].”