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 …

Forgetting refers to the loss or deterioration of previously acquired knowledge. While
existing surveys on forgetting have primarily focused on continual learning, forgetting is a …

Abstract Few-Shot Class-Incremental Learning (FSCIL) aims to learn new classes
incrementally with a limited number of samples per class. It faces issues of forgetting …

Deep Neural Networks (DNNs) have achieved impressive results on the task of image
denoising, but there are two serious problems. First, the denoising ability of DNNs-based …

How to enable learnability for new classes while keeping the capability well on old classes
has been a crucial challenge for class incremental learning. Beyond the normal case, long …

Few-shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes
based on very limited training data without forgetting the old ones encountered. Existing …

Most existing methods for audio classification assume that the vocabulary of audio classes
to be classified is fixed. When novel (unseen) audio classes appear, audio classification …

Few-shot class-incremental learning was introduced to solve the model adaptation problem
for new incremental classes with only a few examples while still remaining effective for old …

Few-shot learning aims to transfer the knowledge learned from seen categories to unseen
categories with a few references. It is also an essential challenge to bridge the gap between …

Deep neural networks are susceptible to catastrophic forgetting when trained on sequential
tasks. Various continual learning (CL) methods often rely on exemplar buffers or/and …