To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

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 …

Lifelong learning offers a promising paradigm of building a generalist agent that learns and
adapts over its lifespan. Unlike traditional lifelong learning problems in image and text …

Real-world scenarios are usually accompanied by continuously appearing classes with
scare labeled samples, which require the machine learning model to incrementally learn …

Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …

A primary goal of class-incremental learning is to strike a balance between stability and
plasticity, where models should be both stable enough to retain knowledge learned from …

The problem of class incremental learning (CIL) is considered. State-of-the-art approaches
use a dynamic architecture based on network expansion (NE), in which a task expert is …

Incremental learning aims to overcome catastrophic forgetting when learning deep networks
from sequential tasks. With impressive learning efficiency and performance, prompt-based …

Abstract In Class-Incremental Learning (CIL) an image classification system is exposed to
new classes in each learning session and must be updated incrementally. Methods …

In this paper, we introduce audio-visual class-incremental learning, a class-incremental
learning scenario for audio-visual video recognition. We demonstrate that joint audio-visual …