中文
相关论文

相关论文: Sub-network Discovery and Soft-masking for Continu…

200 篇论文

Multi-task learning (MTL) has shown great potential in medical image analysis, improving the generalizability of the learned features and the performance in individual tasks. However, most of the work on MTL focuses on either architecture…

计算机视觉与模式识别 · 计算机科学 2023-09-22 Fuping Wu , Le Zhang , Yang Sun , Yuanhan Mo , Thomas Nichols , Bartlomiej W. Papiez

Continual learning (CL) involves acquiring and accumulating knowledge from evolving tasks while alleviating catastrophic forgetting. Recently, leveraging contrastive loss to construct more transferable and less forgetful representations has…

机器学习 · 计算机科学 2025-09-22 Jia Tang , Xinrui Wang , Songcan Chen

Unsupervised Continual Learning (UCL) is a burgeoning field in machine learning, focusing on enabling neural networks to sequentially learn tasks without explicit label information. Catastrophic Forgetting (CF), where models forget…

机器学习 · 计算机科学 2024-05-30 Mohammadreza Sadeghi , Zihan Wang , Narges Armanfard

Continual learning (CL) aims to train deep neural networks efficiently on streaming data while limiting the forgetting caused by new tasks. However, learning transferable knowledge with less interference between tasks is difficult, and…

机器学习 · 计算机科学 2023-10-31 Saurav Jha , Dong Gong , He Zhao , Lina Yao

Large Language Models (LMs) are known to encode world knowledge in their parameters as they pretrain on a vast amount of web corpus, which is often utilized for performing knowledge-dependent downstream tasks such as question answering,…

计算与语言 · 计算机科学 2022-05-25 Joel Jang , Seonghyeon Ye , Sohee Yang , Joongbo Shin , Janghoon Han , Gyeonghun Kim , Stanley Jungkyu Choi , Minjoon Seo

Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. In this work, we focus on continual text classification under the class-incremental setting. Recent CL studies…

计算与语言 · 计算机科学 2023-05-15 Yifan Song , Peiyi Wang , Dawei Zhu , Tianyu Liu , Zhifang Sui , Sujian Li

The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To avoid catastrophic forgetting, various continual learning…

神经与进化计算 · 计算机科学 2022-12-09 Francesco Lässig , Pau Vilimelis Aceituno , Martino Sorbaro , Benjamin F. Grewe

In the literature, many continual learning (CL) algorithms have been proposed to address the issue of catastrophic forgetting in ML models (i.e., learning new tasks leads to the loss of performance on previously learned tasks). Although all…

机器学习 · 计算机科学 2026-05-20 Srijith Nair , Atilla Eryilmaz , Jia , Liu

Inspired by the success of Self-supervised learning (SSL) in learning visual representations from unlabeled data, a few recent works have studied SSL in the context of continual learning (CL), where multiple tasks are learned sequentially,…

计算机视觉与模式识别 · 计算机科学 2023-03-15 Li Yang , Sen Lin , Fan Zhang , Junshan Zhang , Deliang Fan

Building learning agents that can progressively learn and accumulate knowledge is the core goal of the continual learning (CL) research field. Unfortunately, training a model on new data usually compromises the performance on past data. In…

Continual Learning (CL) is a field dedicated to devise algorithms able to achieve lifelong learning. Overcoming the knowledge disruption of previously acquired concepts, a drawback affecting deep learning models and that goes by the name of…

计算机视觉与模式识别 · 计算机科学 2023-01-04 Francesco Pelosin

Recent years have witnessed a burgeoning interest in federated learning (FL). However, the contexts in which clients engage in sequential learning remain under-explored. Bridging FL and continual learning (CL) gives rise to a challenging…

A key stepping stone in the development of an artificial general intelligence (a machine that can perform any task), is the production of agents that can perform multiple tasks at once instead of just one. Unfortunately, canonical methods…

神经与进化计算 · 计算机科学 2019-04-08 Joseph Early

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence. While recent approaches achieve some degree of CL in deep neural networks, they either (1) grow…

机器学习 · 计算机科学 2019-07-15 Blake Camp , Jaya Krishna Mandivarapu , Rolando Estrada

Continual learning (CL) empowers AI systems to progressively acquire knowledge from non-stationary data streams. However, catastrophic forgetting remains a critical challenge. In this work, we identify attention drift in Vision Transformers…

计算机视觉与模式识别 · 计算机科学 2026-02-06 Yue Lu , Xiangyu Zhou , Shizhou Zhang , Yinghui Xing , Guoqiang Liang , Wencong Zhang

Cross-modal retrieval has become a highlighted research topic for retrieval across multimedia data such as image and text. A two-stage learning framework is widely adopted by most existing methods based on Deep Neural Network (DNN): The…

多媒体 · 计算机科学 2017-08-09 Yuxin Peng , Jinwei Qi , Xin Huang , Yuxin Yuan

We present an empirical study on the use of continual learning (CL) methods in a reinforcement learning (RL) scenario, which, to the best of our knowledge, has not been described before. CL is a very active recent research topic concerned…

机器学习 · 计算机科学 2024-09-04 Benedikt Bagus , Alexander Gepperth

Continual learning (CL) aims to enable information systems to learn from a continuous data stream across time. However, it is difficult for existing deep learning architectures to learn a new task without largely forgetting previously…

计算与语言 · 计算机科学 2021-01-11 Magdalena Biesialska , Katarzyna Biesialska , Marta R. Costa-jussà

According to the Complementary Learning Systems (CLS) theory~\cite{mcclelland1995there} in neuroscience, humans do effective \emph{continual learning} through two complementary systems: a fast learning system centered on the hippocampus for…

人工智能 · 计算机科学 2023-07-11 Quang Pham , Chenghao Liu , Steven C. H. Hoi

Rehearsal-based methods have shown superior performance in addressing catastrophic forgetting in continual learning (CL) by storing and training on a subset of past data alongside new data in current task. While such a concurrent rehearsal…

机器学习 · 计算机科学 2025-06-03 Junze Deng , Qinhang Wu , Peizhong Ju , Sen Lin , Yingbin Liang , Ness Shroff