Vision models excel in image classification but struggle to generalize to unseen data, such
as classifying images from unseen domains or discovering novel categories. In this paper …

In the era of deep learning, it's important to obtain enough qualified data for model training.
For the labor-intensive and time-consuming characteristics of data collection and annotation …

Generalized category discovery presents a challenge in a realistic scenario, which requires
the model's generalization ability to recognize unlabeled samples from known and unknown …