A comprehensive survey of forgetting in deep learning beyond continual learning
Forgetting refers to the loss or deterioration of previously acquired knowledge. While
existing surveys on forgetting have primarily focused on continual learning, forgetting is a …
existing surveys on forgetting have primarily focused on continual learning, forgetting is a …
Revisiting class-incremental learning with pre-trained models: Generalizability and adaptivity are all you need
Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …
Revisiting class-incremental learning with pre-trained models: Generalizability and adaptivity are all you need
Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …
Class-incremental learning: A survey
Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …
in many vision tasks in the closed world. However, novel classes emerge from time to time in …
Few-shot class-incremental learning by sampling multi-phase tasks
New classes arise frequently in our ever-changing world, eg, emerging topics in social
media and new types of products in e-commerce. A model should recognize new classes …
media and new types of products in e-commerce. A model should recognize new classes …
Expandable subspace ensemble for pre-trained model-based class-incremental learning
Abstract Class-Incremental Learning (CIL) requires a learning system to continually learn
new classes without forgetting. Despite the strong performance of Pre-Trained Models …
new classes without forgetting. Despite the strong performance of Pre-Trained Models …
Fecam: Exploiting the heterogeneity of class distributions in exemplar-free continual learning
Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits
the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting …
the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting …
Continuous transfer of neural network representational similarity for incremental learning
The incremental learning paradigm in machine learning has consistently been a focus of
academic research. It is similar to the way in which biological systems learn, and reduces …
academic research. It is similar to the way in which biological systems learn, and reduces …
[PDF][PDF] Beef: Bi-compatible class-incremental learning via energy-based expansion and fusion
Neural networks suffer from catastrophic forgetting when sequentially learning tasks phase-
by-phase, making them inapplicable in dynamically updated systems. Class-incremental …
by-phase, making them inapplicable in dynamically updated systems. Class-incremental …
Catastrophic forgetting in deep learning: A comprehensive taxonomy
EL Aleixo, JG Colonna, M Cristo… - arXiv preprint arXiv …, 2023 - arxiv.org
Deep Learning models have achieved remarkable performance in tasks such as image
classification or generation, often surpassing human accuracy. However, they can struggle …
classification or generation, often surpassing human accuracy. However, they can struggle …