The goal of Fed-GCD is to collaboratively train a generic GCD model under the privacy constraint, and then utilize it to discover novel categories in the unlabeled data on the server.

Generalized Category Discovery (GCD) typically relies on the pre-trained Vision Transformer (ViT) to extract features from a global receptive field, followed by contrastive learning to …

Generalized Category Discovery (GCD) aims to identify both known and novel categories in unlabeled data by leveraging knowledge from labeled datasets.

Abstract Generalized Category Discovery (GCD) aims to identify both known and novel categories in unlabeled data by lever-aging knowledge from labeled datasets.

Generalized Category Discovery (GCD) is an intriguing open-world problem that has garnered increasing attention. Given a dataset that includes both labelled and unlabelled images, GCD …

Abstract Generalized Category Discovery (GCD) aims to classify in-puts into both known and novel categories, a task crucial for open-world scientific discoveries. However, current GCD …

To address this issue, we introduce the novel paradigm of Domain Generalization in GCD (DG-GCD), where only source data is available for training, while the target domain--with a distinct …

Generalized Category Discovery (GCD) is a pragmatic and challenging open-world task which endeavors to cluster unlabeled samples from both novel and old classes leveraging some …

Generalized Category Discovery (GCD) is a pragmatic and challenging open-world task, which endeavors to clus-ter unlabeled samples from both novel and old classes, leveraging some …

Generalized category discovery (GCD) is a recently pro-posed open-world problem, which aims to automatically cluster partially labeled data. The main challenge is that the unlabeled data …