CVLC fuses calibrated vision prototypes with LLM-generated language prototypes and applies dual coalescent projection plus latent space reservation to enable few-shot adaptation across sequential domains, reporting up to 16% gains over prior methods.
Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks. Despite recent remarkable progress in state-of-the-art deep learning, deep neural networks (DNNs) are still plagued with the catastrophic forgetting problem. This paper presents a conceptually simple yet general and effective framework for handling catastrophic forgetting in continual learning with DNNs. The proposed method consists of two components: a neural structure optimization component and a parameter learning and/or fine-tuning component. By separating the explicit neural structure learning and the parameter estimation, not only is the proposed method capable of evolving neural structures in an intuitively meaningful way, but also shows strong capabilities of alleviating catastrophic forgetting in experiments. Furthermore, the proposed method outperforms all other baselines on the permuted MNIST dataset, the split CIFAR100 dataset and the Visual Domain Decathlon dataset in continual learning setting.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2verdicts
UNVERDICTED 2roles
background 1polarities
unclear 1representative citing papers
BRAIN uses bias-mitigation continual learning with a new de-bias contrastive loss and angular forgetting mitigation to achieve SOTA performance on vision-brain understanding benchmarks despite brain signal inconsistencies across sessions.
citing papers explorer
-
Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation
CVLC fuses calibrated vision prototypes with LLM-generated language prototypes and applies dual coalescent projection plus latent space reservation to enable few-shot adaptation across sequential domains, reporting up to 16% gains over prior methods.
-
BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding
BRAIN uses bias-mitigation continual learning with a new de-bias contrastive loss and angular forgetting mitigation to achieve SOTA performance on vision-brain understanding benchmarks despite brain signal inconsistencies across sessions.