H Lin, S Feng, X Li, W Li, Y Ye - IEEE Transactions on Circuits …, 2022 - ieeexplore.ieee.org
Online class-incremental learning (OCIL) studies the problem of mitigating the phenomenon of catastrophic forgetting while learning new classes from a continuously non-stationary data …
J Yoon, SJ Hwang, Y Cao - International Conference on …, 2023 - proceedings.mlr.press
Motivated by the efficiency and rapid convergence of pre-trained models for solving downstream tasks, this paper extensively studies the impact of Continual Learning (CL) …
X Li, S Wang, J Sun, Z Xu - IEEE Transactions on Pattern …, 2023 - ieeexplore.ieee.org
Deep neural networks suffer from catastrophic forgetting when trained on sequential tasks in continual learning. Various methods rely on storing data of previous tasks to mitigate …
Sensor-based human activity recognition (HAR), ie, the ability to discover human daily activity patterns from wearable or embedded sensors, is a key enabler for many real-world …
Deep learning based food recognition has achieved remarkable progress in predicting food types given an eating occasion image. However, there are two major obstacles that hinder …
F Mi, X Lin, B Faltings - Proceedings of the 14th ACM Conference on …, 2020 - dl.acm.org
Session-based recommendation has received growing attention recently due to the increasing privacy concern. Despite the recent success of neural session-based …
P Li, H Yu, X Luo, J Wu - IEEE Transactions on Big Data, 2023 - ieeexplore.ieee.org
Graphs have been widely adopted to accomplish fraud detection tasks because of their inherently favorable structure to capture the intricate features in many complicated …
Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training …
Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former ones …