中文
相关论文

相关论文: An Investigation of Replay-based Approaches for Co…

200 篇论文

Continual learning refers to the capability of a machine learning model to learn and adapt to new information, without compromising its performance on previously learned tasks. Although several studies have investigated continual learning…

信息检索 · 计算机科学 2024-06-21 Jingrui Hou , Georgina Cosma , Axel Finke

Continual learning (CL) is an approach to address catastrophic forgetting, which refers to forgetting previously learned knowledge by neural networks when trained on new tasks or data distributions. The adversarial robustness has decomposed…

机器学习 · 计算机科学 2023-07-04 Hikmat Khan , Nidhal C. Bouaynaya , Ghulam Rasool

Continual learning aims to learn on non-stationary data streams without catastrophically forgetting previous knowledge. Prevalent replay-based methods address this challenge by rehearsing on a small buffer holding the seen data, for which a…

机器学习 · 计算机科学 2023-04-21 Zhicheng Sun , Yadong Mu , Gang Hua

The design of machines and algorithms capable of learning in a dynamically changing environment has become an increasingly topical problem with the increase of the size and heterogeneity of data available to learning systems. As a…

计算机视觉与模式识别 · 计算机科学 2022-05-02 Francesco Pelosin , Andrea Torsello

Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The key challenge in FCCL is catastrophic forgetting, an issue…

机器学习 · 计算机科学 2024-09-05 Jinglin Liang , Jin Zhong , Hanlin Gu , Zhongqi Lu , Xingxing Tang , Gang Dai , Shuangping Huang , Lixin Fan , Qiang Yang

We present a new replay-based method of continual classification learning that we term "conditional replay" which generates samples and labels together by sampling from a distribution conditioned on the class. We compare conditional replay…

机器学习 · 计算机科学 2019-07-02 Timothée Lesort , Alexander Gepperth , Andrei Stoian , David Filliat

Continual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains. A central challenge in Continual Learning…

计算机视觉与模式识别 · 计算机科学 2022-09-21 Tobias Kalb , Björn Mauthe , Jürgen Beyerer

Scenarios in which restrictions in data transfer and storage limit the possibility to compose a single dataset -- also exploiting different data sources -- to perform a batch-based training procedure, make the development of robust models…

计算机视觉与模式识别 · 计算机科学 2023-07-31 Lorenzo Pellegrini , Guido Borghi , Annalisa Franco , Davide Maltoni

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…

机器学习 · 计算机科学 2019-11-27 David Rolnick , Arun Ahuja , Jonathan Schwarz , Timothy P. Lillicrap , Greg Wayne

Continual learning is the process of training machine learning models on a sequence of tasks where data distributions change over time. A well-known obstacle in this setting is catastrophic forgetting, a phenomenon in which a model…

机器学习 · 计算机科学 2025-02-18 Andrii Krutsylo

Continual learning is the ability to sequentially learn over time by accommodating knowledge while retaining previously learned experiences. Neural networks can learn multiple tasks when trained on them jointly, but cannot maintain…

机器学习 · 计算机科学 2018-10-26 Frantzeska Lavda , Jason Ramapuram , Magda Gregorova , Alexandros Kalousis

Curriculum learning (CL) is a training strategy that trains a machine learning model from easier data to harder data, which imitates the meaningful learning order in human curricula. As an easy-to-use plug-in, the CL strategy has…

机器学习 · 计算机科学 2021-03-26 Xin Wang , Yudong Chen , Wenwu Zhu

Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new tasks). Due to the fact that past training data is not…

机器学习 · 计算机科学 2022-09-27 Qing Sun , Fan Lyu , Fanhua Shang , Wei Feng , Liang Wan

Rehearsal-based Continual Learning (CL) has been intensely investigated in Deep Neural Networks (DNNs). However, its application in Spiking Neural Networks (SNNs) has not been explored in depth. In this paper we introduce the first…

神经与进化计算 · 计算机科学 2024-12-23 Alberto Dequino , Alessio Carpegna , Davide Nadalini , Alessandro Savino , Luca Benini , Stefano Di Carlo , Francesco Conti

A continual learning (CL) algorithm learns from a non-stationary data stream. The non-stationarity is modeled by some schedule that determines how data is presented over time. Most current methods make strong assumptions on the schedule and…

机器学习 · 计算机科学 2022-10-17 Ruohan Wang , Marco Ciccone , Giulia Luise , Andrew Yapp , Massimiliano Pontil , Carlo Ciliberto

Continual learning (CL) in deep neural networks (DNNs) involves incrementally accumulating knowledge in a DNN from a growing data stream. A major challenge in CL is that non-stationary data streams cause catastrophic forgetting of…

机器学习 · 计算机科学 2024-05-02 Md Yousuf Harun , Jhair Gallardo , Junyu Chen , Christopher Kanan

With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly important. In this paper, we propose a new continual learning…

计算机视觉与模式识别 · 计算机科学 2021-03-09 Bo Zhao , Shixiang Tang , Dapeng Chen , Hakan Bilen , Rui Zhao

With the digitization of modern cities, large data volumes and powerful computational resources facilitate the rapid update of intelligent models deployed in smart cities. Continual learning (CL) is a novel machine learning paradigm that…

机器学习 · 计算机科学 2024-04-02 Li Yang , Zhipeng Luo , Shiming Zhang , Fei Teng , Tianrui Li

Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly,…

机器学习 · 计算机科学 2020-12-15 Xu Ji , Joao Henriques , Tinne Tuytelaars , Andrea Vedaldi

Continual learning (CL) is crucial for language models to dynamically adapt to the evolving real-world demands. To mitigate the catastrophic forgetting problem in CL, data replay has been proven a simple and effective strategy, and the…

计算与语言 · 计算机科学 2024-11-12 Jinghan He , Haiyun Guo , Kuan Zhu , Zihan Zhao , Ming Tang , Jinqiao Wang