In contrast to batch learning where all training data is available at once, continual learning
represents a family of methods that accumulate knowledge and learn continuously with data …

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 …

Abstract Large Vision & Language models pretrained on web-scale data provide
representations that are invaluable for numerous V &L problems. However, it is unclear how …

Online continual learning from data streams in dynamic environments is a critical direction in
the computer vision field. However, realistic benchmarks and fundamental studies in this line …

Catastrophic forgetting (CF) frequently occurs when learning with non-stationary data
distribution. The CF issue remains nearly unexplored and is more challenging when meta …

Large language models encode impressively broad world knowledge in their parameters.
However, the knowledge in static language models falls out of date, limiting the model's …

Few-shot classification (FSC) entails learning novel classes given only a few examples per
class after a pre-training (or meta-training) phase on a set of base classes. Recent works …

Over the past decade, deep neural networks have demonstrated significant success using
the training scheme that involves mini-batch stochastic gradient descent on extensive …

With the recent development of deep learning, AI models are widely used in various
domains. AI models show good performance for definite tasks such as image classification …

Rehearsal is a critical component for class-incremental continual learning, yet it requires a
substantial memory budget. Our work investigates whether we can significantly reduce this …