In contrast to batch learning where all training data is available at once, continual learning represents a family of methods that accumulate knowledge and learn continuously with data …
SM Park, YG Kim - IEEE access, 2022 - ieeexplore.ieee.org
Unlike previous studies on the Metaverse based on Second Life, the current Metaverse is based on the social value of Generation Z that online and offline selves are not different …
Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in …
The lifelong learning paradigm in machine learning is an attractive alternative to the more prominent isolated learning scheme not only due to its resemblance to biological learning …
X Liu, YS Hu, XS Cao, AD Bagdanov, K Li… - … on Computer Vision, 2022 - Springer
In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones. However, conventional CIL methods consider a balanced …
Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly …
Current deep reinforcement learning (RL) algorithms are still highly task-specific and lack the ability to generalize to new environments. Lifelong learning (LLL), however, aims at …
The subpopulation shifting challenge, known as some subpopulations of a category that are not seen during training, severely limits the classification performance of the state-of-the-art …
X Xiang, Y Tan, Q Wan, J Ma, A Yuille… - European Conference on …, 2022 - Springer
Different from fine-tuning models pre-trained on a large-scale dataset of preset classes, class-incremental learning (CIL) aims to recognize novel classes over time without forgetting …