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 …
Representation compensation networks for continual semantic segmentation
In this work, we study the continual semantic segmentation problem, where the deep neural
networks are required to incorporate new classes continually without catastrophic forgetting …
networks are required to incorporate new classes continually without catastrophic forgetting …
Endpoints weight fusion for class incremental semantic segmentation
Class incremental semantic segmentation (CISS) focuses on alleviating catastrophic
forgetting to improve discrimination. Previous work mainly exploit regularization (eg …
forgetting to improve discrimination. Previous work mainly exploit regularization (eg …
Online continual learning on a contaminated data stream with blurry task boundaries
Learning under a continuously changing data distribution with incorrect labels is a desirable
real-world problem yet challenging. Large body of continual learning (CL) methods …
real-world problem yet challenging. Large body of continual learning (CL) methods …
Bilevel coreset selection in continual learning: A new formulation and algorithm
Coreset is a small set that provides a data summary for a large dataset, such that training
solely on the small set achieves competitive performance compared with a large dataset. In …
solely on the small set achieves competitive performance compared with a large dataset. In …
Cnll: A semi-supervised approach for continual noisy label learning
N Karim, U Khalid, A Esmaeili… - Proceedings of the …, 2022 - openaccess.thecvf.com
The task of continual learning requires careful design of algorithms that can tackle
catastrophic forgetting. However, the noisy label, which is inevitable in a real-world scenario …
catastrophic forgetting. However, the noisy label, which is inevitable in a real-world scenario …
Learning Equi-angular Representations for Online Continual Learning
Online continual learning suffers from an underfitted solution due to insufficient training for
prompt model updates (eg single-epoch training). To address the challenge we propose an …
prompt model updates (eg single-epoch training). To address the challenge we propose an …
Metamix: Towards corruption-robust continual learning with temporally self-adaptive data transformation
Continual Learning (CL) has achieved rapid progress in recent years. However, it is still
largely unknown how to determine whether a CL model is trustworthy and how to foster its …
largely unknown how to determine whether a CL model is trustworthy and how to foster its …
Inherit with distillation and evolve with contrast: Exploring class incremental semantic segmentation without exemplar memory
As a front-burner problem in incremental learning, class incremental semantic segmentation
(CISS) is plagued by catastrophic forgetting and semantic drift. Although recent methods …
(CISS) is plagued by catastrophic forgetting and semantic drift. Although recent methods …
SIESTA: Efficient online continual learning with sleep
In supervised continual learning, a deep neural network (DNN) is updated with an ever-
growing data stream. Unlike the offline setting where data is shuffled, we cannot make any …
growing data stream. Unlike the offline setting where data is shuffled, we cannot make any …