A comprehensive survey of continual learning: theory, method and application
To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …
Hierarchical decomposition of prompt-based continual learning: Rethinking obscured sub-optimality
Prompt-based continual learning is an emerging direction in leveraging pre-trained
knowledge for downstream continual learning, and has almost reached the performance …
knowledge for downstream continual learning, and has almost reached the performance …
Ranpac: Random projections and pre-trained models for continual learning
MD McDonnell, D Gong, A Parvaneh… - Advances in …, 2024 - proceedings.neurips.cc
Continual learning (CL) aims to incrementally learn different tasks (such as classification) in
a non-stationary data stream without forgetting old ones. Most CL works focus on tackling …
a non-stationary data stream without forgetting old ones. Most CL works focus on tackling …
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 …
Online continual learning without the storage constraint
Traditional online continual learning (OCL) research has primarily focused on mitigating
catastrophic forgetting with fixed and limited storage allocation throughout an agent's …
catastrophic forgetting with fixed and limited storage allocation throughout an agent's …
Continual learning: Applications and the road forward
Continual learning is a sub-field of machine learning, which aims to allow machine learning
models to continuously learn on new data, by accumulating knowledge without forgetting …
models to continuously learn on new data, by accumulating knowledge without forgetting …
Continually learning representations at scale
Many widely used continual learning benchmarks follow a protocol that starts from an
untrained, randomly initialized model that needs to sequentially learn a number of incoming …
untrained, randomly initialized model that needs to sequentially learn a number of incoming …
Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer
Class-incremental learning (CIL) aims to enable models to continuously learn new classes
while overcoming catastrophic forgetting. The introduction of pre-trained models has brought …
while overcoming catastrophic forgetting. The introduction of pre-trained models has brought …
Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
D Goswami, B Twardowski… - Proceedings of the …, 2024 - openaccess.thecvf.com
Few-shot class-incremental learning (FSCIL) aims to adapt the model to new classes from
very few data (5 samples) without forgetting the previously learned classes. Recent works in …
very few data (5 samples) without forgetting the previously learned classes. Recent works in …
HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning
The deployment of pre-trained models (PTMs) has greatly advanced the field of continual
learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgetting …
learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgetting …