中文
相关论文

相关论文: I2CANSAY:Inter-Class Analogical Augmentation and I…

200 篇论文

Online continual learning (OCL) aims to enable model learning from a non-stationary data stream to continuously acquire new knowledge as well as retain the learnt one, under the constraints of having limited system size and computational…

计算机视觉与模式识别 · 计算机科学 2023-01-16 Sheng-Feng Yu , Wei-Chen Chiu

The dynamic expansion architecture is becoming popular in class incremental learning, mainly due to its advantages in alleviating catastrophic forgetting. However, task confusion is not well assessed within this framework, e.g., the…

计算机视觉与模式识别 · 计算机科学 2023-01-04 Bingchen Huang , Zhineng Chen , Peng Zhou , Jiayin Chen , Zuxuan Wu

To imitate the ability of keeping learning of human, continual learning which can learn from a never-ending data stream has attracted more interests recently. In all settings, the online class incremental learning (OCIL), where incoming…

计算机视觉与模式识别 · 计算机科学 2023-10-20 Guoqiang Liang , Zhaojie Chen , Zhaoqiang Chen , Shiyu Ji , Yanning Zhang

The main challenge of continual learning is \textit{catastrophic forgetting}. Because of processing data in one pass, online continual learning (OCL) is one of the most difficult continual learning scenarios. To address catastrophic…

机器学习 · 计算机科学 2025-10-02 Aopeng Wang , Ke Deng , Yongli Ren , Jun Luo

In autonomous driving, even a meticulously trained model can encounter failures when facing unfamiliar scenarios. One of these scenarios can be formulated as an online continual learning (OCL) problem. That is, data come in an online…

机器学习 · 计算机科学 2024-11-06 Huiping Zhuang , Di Fang , Kai Tong , Yuchen Liu , Ziqian Zeng , Xu Zhou , Cen Chen

Despite rapid advances in continual learning, a large body of research is devoted to improving performance in the existing setups. While a handful of work do propose new continual learning setups, they still lack practicality in certain…

机器学习 · 计算机科学 2022-03-22 Hyunseo Koh , Dahyun Kim , Jung-Woo Ha , Jonghyun Choi

Online continual learning for image classification studies the problem of learning to classify images from an online stream of data and tasks, where tasks may include new classes (class incremental) or data nonstationarity (domain…

机器学习 · 计算机科学 2021-10-06 Zheda Mai , Ruiwen Li , Jihwan Jeong , David Quispe , Hyunwoo Kim , Scott Sanner

Exemplar-Free Class Incremental Learning (efCIL) aims to continuously incorporate the knowledge from new classes while retaining previously learned information, without storing any old-class exemplars (i.e., samples). For this purpose,…

计算机视觉与模式识别 · 计算机科学 2024-03-26 Libo Huang , Zhulin An , Yan Zeng , Chuanguang Yang , Xinqiang Yu , Yongjun Xu

Traditional online continual learning (OCL) research has primarily focused on mitigating catastrophic forgetting with fixed and limited storage allocation throughout an agent's lifetime. However, a broad range of real-world applications are…

计算机视觉与模式识别 · 计算机科学 2023-11-03 Ameya Prabhu , Zhipeng Cai , Puneet Dokania , Philip Torr , Vladlen Koltun , Ozan Sener

Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the…

计算机视觉与模式识别 · 计算机科学 2021-07-09 Kai Wang , Luis Herranz , Joost van de Weijer

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

计算与语言 · 计算机科学 2023-10-11 Yifan Song , Peiyi Wang , Weimin Xiong , Dawei Zhu , Tianyu Liu , Zhifang Sui , Sujian Li

Continual Learning (CL) aims to incrementally acquire new knowledge while mitigating catastrophic forgetting. Within this setting, Online Continual Learning (OCL) focuses on updating models promptly and incrementally from single or small…

机器学习 · 计算机科学 2025-12-19 Giovanni Donghi , Luca Pasa , Daniele Zambon , Cesare Alippi , Nicolò Navarin

Continual learning in online scenario aims to learn a sequence of new tasks from data stream using each data only once for training, which is more realistic than in offline mode assuming data from new task are all available. However, this…

计算机视觉与模式识别 · 计算机科学 2021-10-19 Jiangpeng He , Fengqing Zhu

Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning. However, the incremental learning issue of CL has rarely been…

机器学习 · 计算机科学 2023-01-31 Cheng Ji , Jianxin Li , Hao Peng , Jia Wu , Xingcheng Fu , Qingyun Sun , Phillip S. Yu

Online continual learning requires the models to learn from constant, endless streams of data. While significant efforts have been made in this field, most were focused on mitigating the catastrophic forgetting issue to achieve better…

机器学习 · 计算机科学 2024-10-14 Xinrui Wang , Chuanxing Geng , Wenhai Wan , Shao-yuan Li , Songcan Chen

In-context Learning (ICL) empowers large language models (LLMs) to swiftly adapt to unseen tasks at inference-time by prefixing a few demonstration examples before queries. Despite its versatility, ICL incurs substantial computational and…

机器学习 · 计算机科学 2025-02-26 Zhuowei Li , Zihao Xu , Ligong Han , Yunhe Gao , Song Wen , Di Liu , Hao Wang , Dimitris N. Metaxas

For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the…

机器学习 · 计算机科学 2022-10-12 Marc Masana , Xialei Liu , Bartlomiej Twardowski , Mikel Menta , Andrew D. Bagdanov , Joost van de Weijer

Current research on class-incremental learning primarily focuses on single-label classification tasks. However, real-world applications often involve multi-label scenarios, such as image retrieval and medical imaging. Therefore, this paper…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Chenhao Ding , Songlin Dong , Zhengdong Zhou , Jizhou Han , Qiang Wang , Yuhang He , Yihong Gong

Continual learning (or class incremental learning) is a realistic learning scenario for computer vision systems, where deep neural networks are trained on episodic data, and the data from previous episodes are generally inaccessible to the…

计算机视觉与模式识别 · 计算机科学 2026-02-05 Aditya R. Bhattacharya , Debanjan Goswami , Shayok Chakraborty

Class incremental learning (CIL) requires an agent to learn distinct tasks consecutively with knowledge retention against forgetting. Problems impeding the practical applications of CIL methods are twofold: (1) non-i.i.d batch streams and…

机器学习 · 计算机科学 2025-10-27 Junda Wang , Minghui Hu , Ning Li , Abdulaziz Al-Ali , Ponnuthurai Nagaratnam Suganthan
‹ 上一页 1 2 3 10 下一页 ›