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 …
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 …
A closer look at rehearsal-free continual learning
Continual learning is a setting where machine learning models learn novel concepts from
continuously shifting training data, while simultaneously avoiding degradation of knowledge …
continuously shifting training data, while simultaneously avoiding degradation of knowledge …
Training networks in null space of feature covariance for continual learning
In the setting of continual learning, a network is trained on a sequence of tasks, and suffers
from catastrophic forgetting. To balance plasticity and stability of network in continual …
from catastrophic forgetting. To balance plasticity and stability of network in continual …
Online class-incremental continual learning with adversarial shapley value
As image-based deep learning becomes pervasive on every device, from cell phones to
smart watches, there is a growing need to develop methods that continually learn from data …
smart watches, there is a growing need to develop methods that continually learn from data …
Self-evolved dynamic expansion model for task-free continual learning
Abstract Task-Free Continual Learning (TFCL) aims to learn new concepts from a stream of
data without any task information. The Dynamic Expansion Model (DEM) has shown …
data without any task information. The Dynamic Expansion Model (DEM) has shown …
Continual learning based on ood detection and task masking
Existing continual learning techniques focus on either task incremental learning (TIL) or
class incremental learning (CIL) problem, but not both. CIL and TIL differ mainly in that the …
class incremental learning (CIL) problem, but not both. CIL and TIL differ mainly in that the …
InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning
YS Liang, WJ Li - Proceedings of the IEEE/CVF Conference …, 2024 - openaccess.thecvf.com
Continual learning requires the model to learn multiple tasks sequentially. In continual
learning the model should possess the ability to maintain its performance on old tasks …
learning the model should possess the ability to maintain its performance on old tasks …
Generating instance-level prompts for rehearsal-free continual learning
Abstract We introduce Domain-Adaptive Prompt (DAP), a novel method for continual
learning using Vision Transformers (ViT). Prompt-based continual learning has recently …
learning using Vision Transformers (ViT). Prompt-based continual learning has recently …
Consistent Prompting for Rehearsal-Free Continual Learning
Continual learning empowers models to adapt autonomously to the ever-changing
environment or data streams without forgetting old knowledge. Prompt-based approaches …
environment or data streams without forgetting old knowledge. Prompt-based approaches …