The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is …
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 …
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; …
Y Guo, B Liu, D Zhao - International conference on machine …, 2022 - proceedings.mlr.press
This paper proposed a new online continual learning approach called OCM based on mutual information (MI) maximization. It achieves two objectives that are critical in dealing …
Online continual learning for image classification studies the problem of learning to classify images from an online stream of data and tasks, where tasks may include new classes …
We discuss a general formulation for the Continual Learning (CL) problem for classification— a learning task where a stream provides samples to a learner and the goal of the learner …
Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase …
State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's …
A Cheraghian, S Rahman, P Fang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner. Due to the …