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 …

Novel classes frequently arise in our dynamically changing world, eg, new users in the
authentication system, and a machine learning model should recognize new classes without …

The staple of human intelligence is the capability of acquiring knowledge in a continuous
fashion. In stark contrast, Deep Networks forget catastrophically and, for this reason, the sub …

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 …

Few-shot class-incremental learning (FSCIL) is designed to incrementally recognize novel
classes with only few training samples after the (pre-) training on base classes with sufficient …

Online continual learning suffers from an underfitted solution due to insufficient training for
prompt model updates (eg single-epoch training). To address the challenge we propose an …

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 …

In this paper, we focus on a general yet important learning problem, pairwise similarity
learning (PSL). PSL subsumes a wide range of important applications, such as open-set …

Learning compatible representations enables the interchangeable use of semantic features
as models are updated over time. This is particularly relevant in search and retrieval systems …

Few-shot class-incremental learning (FSCIL) confronts the challenge of integrating new
classes into a model with minimal training samples while preserving the knowledge of …