This paper focuses on the prevalent stage interference and stage performance imbalance of incremental learning. To avoid obvious stage learning bottlenecks, we propose a new …
The influence of class orderings in the evaluation of incremental learning has received very little attention. In this paper, we investigate the impact of class orderings for incrementally …
Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned …
R Aljundi - arXiv preprint arXiv:1910.02718, 2019 - arxiv.org
Artificial neural networks have exceeded human-level performance in accomplishing several individual tasks (eg voice recognition, object recognition, and video games) …
E Belouadah, A Popescu, I Kanellos - arXiv preprint arXiv:2008.13710, 2020 - arxiv.org
Incremental Learning (IL) is useful when artificial systems need to deal with streams of data and do not have access to all data at all times. The most challenging setting requires a …
Despite the impressive performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning new tasks incrementally. Recently, various …
Y Luo, L Yin, W Bai, K Mao - Entropy, 2020 - mdpi.com
As a special case of machine learning, incremental learning can acquire useful knowledge from incoming data continuously while it does not need to access the original data. It is …
J He, R Mao, Z Shao, F Zhu - Proceedings of the IEEE/CVF …, 2020 - openaccess.thecvf.com
Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data. However, there are two major …
Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a …