[HTML][HTML] Managing the unknown in machine learning: Definitions, related areas, recent advances, and prospects

M Barcina-Blanco, JL Lobo, P Garcia-Bringas… - Neurocomputing, 2024 - Elsevier
In the rapidly evolving domain of machine learning, the ability to adapt to unforeseen
circumstances and novel data types is of paramount importance. The deployment of Artificial …

A survey on continual semantic segmentation: Theory, challenge, method and application

B Yuan, D Zhao - IEEE Transactions on Pattern Analysis and …, 2024 - ieeexplore.ieee.org
Continual learning, also known as incremental learning or life-long learning, stands at the
forefront of deep learning and AI systems. It breaks through the obstacle of one-way training …

Is continual learning ready for real-world challenges?

T Kontogianni, Y Yue, S Tang, K Schindler - ar** a reliable vision system is a fundamental challenge for robotic technologies (eg,
indoor service robots and outdoor autonomous robots) which can ensure reliable navigation …

IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation

X Yu, Y Fang, Y Zhao, Y Wei - arxiv preprint arxiv:2502.04870, 2025 - arxiv.org
Class incremental learning aims to enable models to learn from sequential, non-stationary
data streams across different tasks without catastrophic forgetting. In class incremental …

[HTML][HTML] A Survey of Continual Learning with Deep Networks: Theory, Method and Application

Z Dongyang, LU Zixuan, LIU Junmin, LI Lanyu - 电子与信息学报, 2024 - jeit.ac.cn
Biological organisms in nature are required to continuously learn from and adapt to the
environment throughout their lifetime. This ongoing learning capacity serves as the …

[HTML][HTML] 深度模型的持续学**综述: 理论, 方法和应用

张东阳, 陆子轩, 刘军民, **澜宇 - 电子与信息学报, 2024 - jeit.ac.cn
自然界中的生物需要在其一生中不断地学**并适应环境, 这种持续学**的能力是生物学**系统的
基础. 尽管深度学**方法在计算机视觉和自然语言处理领域取得了重要进展 …