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 …

Artificial intelligence research has seen enormous progress over the past few decades, but it
predominantly relies on fixed datasets and stationary environments. Continual learning is an …

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 condensation aims at reducing the network training effort through condensing a
cumbersome training set into a compact synthetic one. State-of-the-art approaches largely …

Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with
only unlabeled test data streams. Most of the previous TTA methods have achieved great …

Recent breakthroughs in self-supervised learning show that such algorithms learn visual
representations that can be transferred better to unseen tasks than cross-entropy based …

Computational cost of training state-of-the-art deep models in many learning problems is
rapidly increasing due to more sophisticated models and larger datasets. A recent promising …

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; …

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 …