Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for …
Incrementally learning new information from a non-stationary stream of data, referred to as 'continual learning', is a key feature of natural intelligence, but a challenging problem for …
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; …
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 …
Continual learning (CL) can help pre-trained vision-language models efficiently adapt to new or under-trained data distributions without re-training. Nevertheless, during the …
H Ahn, J Kwak, S Lim, H Bang… - Proceedings of the …, 2021 - openaccess.thecvf.com
We consider class incremental learning (CIL) problem, in which a learning agent continuously learns new classes from incrementally arriving training data batches and aims …
G Petit, A Popescu, H Schindler… - Proceedings of the …, 2023 - openaccess.thecvf.com
Exemplar-free class-incremental learning is very challenging due to the negative effect of catastrophic forgetting. A balance between stability and plasticity of the incremental process …
Z Ke, B Liu - arXiv preprint arXiv:2211.12701, 2022 - arxiv.org
Continual learning (CL) is a learning paradigm that emulates the human capability of learning and accumulating knowledge continually without forgetting the previously learned …
Abstract The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. The efforts of researchers have …