Large deep learning models are impressive, but they struggle when real-time data is not
available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for …

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 …

Traditional classifiers are deployed under closed-set setting, with both training and test
classes belong to the same set. However, real-world applications probably face the input of …

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 …

New classes arise frequently in our ever-changing world, eg, emerging topics in social
media and new types of products in e-commerce. A model should recognize new classes …

Few-shot class incremental learning (FSCIL) aims to address catastrophic forgetting during
class incremental learning in a few-shot learning setting. In this paper, we approach the …

Continual learning from a sequential stream of data is a crucial challenge for machine
learning research. Most studies have been conducted on this topic under the single-label …

Learning from large-scale contrastive language-image pre-training like CLIP has shown
remarkable success in a wide range of downstream tasks recently, but it is still under …

Traditional learning systems are trained in closed-world for a fixed number of classes, and
need pre-collected datasets in advance. However, new classes often emerge in real-world …

Real-world visual recognition requires handling the extreme sample imbalance in large-
scale long-tailed data. We propose a" divide&conquer" strategy for the challenging LVIS …