An appraisal of incremental learning methods

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 …

Generative models from the perspective of continual learning

T Lesort, H Caselles-Dupré… - … Joint Conference on …, 2019 - ieeexplore.ieee.org
Which generative model is the most suitable for Continual Learning? This paper aims at
evaluating and comparing generative models on disjoint sequential image generation tasks …

Learn#: A Novel incremental learning method for text classification

G Shan, S Xu, L Yang, S Jia, Y **ang - Expert Systems with Applications, 2020 - Elsevier
Deep learning is an effective method for extracting the underlying information in text.
However, it performs better on closed datasets and is less effective in real-world scenarios …

A new knowledge distillation for incremental object detection

L Chen, C Yu, L Chen - 2019 International Joint Conference on …, 2019 - ieeexplore.ieee.org
Nowadays, the Convolutional Neural Network is successfully applied to the images object
detection. When new classes of object emerges, it is popular to adapt the convolutional …

Measuring asymmetric gradient discrepancy in parallel continual learning

F Lyu, Q Sun, F Shang, L Wan… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract In Parallel Continual Learning (PCL), the parallel multiple tasks start and end
training unpredictably, thus suffering from training conflict and catastrophic forgetting issues …

Marginal replay vs conditional replay for continual learning

T Lesort, A Gepperth, A Stoian, D Filliat - International Conference on …, 2019 - Springer
We present a new replay-based method of continual classification learning that we term
“conditional replay” which generates samples and labels together by sampling from a …

Elastic Multi-Gradient Descent for Parallel Continual Learning

F Lyu, W Feng, Y Li, Q Sun, F Shang, L Wan… - arxiv preprint arxiv …, 2024 - arxiv.org
The goal of Continual Learning (CL) is to continuously learn from new data streams and
accomplish the corresponding tasks. Previously studied CL assumes that data are given in …

Continual learning: Tackling catastrophic forgetting in deep neural networks with replay processes

T Lesort - arxiv preprint arxiv:2007.00487, 2020 - arxiv.org
Humans learn all their life long. They accumulate knowledge from a sequence of learning
experiences and remember the essential concepts without forgetting what they have learned …

Towards stable training of parallel continual learning

L Yuepan, F Lyu, Y Li, W Feng, G Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
Parallel Continual Learning (PCL) tasks investigate the training methods for continual
learning with multi-source input, where data from different tasks are learned as they arrive …

Apprentissage continu: S'attaquer à l'oubli foudroyant des réseaux de neurones profonds grâce aux méthodes à rejeu de données

T Lesort - 2020 - theses.hal.science
Humans learn all their life long. They accumulate knowledge from a sequence of learning
experiences and remember the essential concepts without forgetting what they have learned …