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 …

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

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 …

The ultimate goal of C-GCD is to discover novel classes while keeping the old knowledge without forgetting. We propose a meta-learning based optimization strategy to directly optimize the …

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.

We thoroughly evaluate HypCD on public GCD benchmarks, by applying it to various baseline and state-of-the-art methods, consistently achieving significant improvements.

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 …

Abstract Given unlabelled datasets containing both old and new cat-egories, generalized category discovery (GCD) aims to ac-curately discover new classes while correctly classifying old …

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 …

GCD aims to learn a model capable of accurately classify-ing unlabelled samples from known categories while simul-taneously clustering those from unknown categories.