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 …

Recent success of deep learning is largely attributed to the sheer amount of data used for
training deep neural networks. Despite the unprecedented success, the massive data …

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 …

We present a novel class incremental learning approach based on deep neural networks,
which continually learns new tasks with limited memory for storing examples in the previous …

Dataset distillation aims to learn a small synthetic dataset that preserves most of the
information from the original dataset. Dataset distillation can be formulated as a bi-level …

Federated learning (FL) has attracted growing attentions via data-private collaborative
training on decentralized clients. However, most existing methods unrealistically assume …

Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms
that can continually learn new concepts from a few data points, without forgetting knowledge …

Non-exemplar class-incremental learning is to recognize both the old and new classes
when old class samples cannot be saved. It is a challenging task since representation …

Incremental object detection (IOD) aims to train an object detector in phases, each with
annotations for new object categories. As other incremental settings, IOD is subject to …

This paper considers incremental few-shot learning, which requires a model to continually
recognize new categories with only a few examples provided. Our study shows that existing …