Component Adaptive Clustering for Generalized Category Discovery
This addresses the challenge of generalized category discovery in partially labeled image datasets for computer vision applications, offering an incremental improvement by removing the need for predefined class counts.
The paper tackles the problem of categorizing unlabeled images into known and novel classes without prior knowledge of the number of unknown categories, proposing AdaGCD which dynamically determines the optimal number of slots based on data complexity, achieving improved class discovery in open-world scenarios as validated on public and fine-grained datasets.
Generalized Category Discovery (GCD) tackles the challenging problem of categorizing unlabeled images into both known and novel classes within a partially labeled dataset, without prior knowledge of the number of unknown categories. Traditional methods often rely on rigid assumptions, such as predefining the number of classes, which limits their ability to handle the inherent variability and complexity of real-world data. To address these shortcomings, we propose AdaGCD, a cluster-centric contrastive learning framework that incorporates Adaptive Slot Attention (AdaSlot) into the GCD framework. AdaSlot dynamically determines the optimal number of slots based on data complexity, removing the need for predefined slot counts. This adaptive mechanism facilitates the flexible clustering of unlabeled data into known and novel categories by dynamically allocating representational capacity. By integrating adaptive representation with dynamic slot allocation, our method captures both instance-specific and spatially clustered features, improving class discovery in open-world scenarios. Extensive experiments on public and fine-grained datasets validate the effectiveness of our framework, emphasizing the advantages of leveraging spatial local information for category discovery in unlabeled image datasets.