GLEAN: Generalized Category Discovery with Diverse and Quality-Enhanced LLM Feedback
This addresses the challenge of costly human annotation in open-world recognition tasks, offering a more efficient solution for applications like image classification, though it appears incremental by building on existing GCD methods with LLM integration.
The paper tackles the problem of Generalized Category Discovery (GCD), which involves recognizing both known and novel categories in unlabeled data with limited labeled data, by proposing GLEAN, a framework that uses diverse and quality-enhanced LLM feedback to improve performance, achieving superior results over state-of-the-art models across various datasets and metrics.
Generalized Category Discovery (GCD) is a practical and challenging open-world task that aims to recognize both known and novel categories in unlabeled data using limited labeled data from known categories. Due to the lack of supervision, previous GCD methods face significant challenges, such as difficulty in rectifying errors for confusing instances, and inability to effectively uncover and leverage the semantic meanings of discovered clusters. Therefore, additional annotations are usually required for real-world applicability. However, human annotation is extremely costly and inefficient. To address these issues, we propose GLEAN, a unified framework for generalized category discovery that actively learns from diverse and quality-enhanced LLM feedback. Our approach leverages three different types of LLM feedback to: (1) improve instance-level contrastive features, (2) generate category descriptions, and (3) align uncertain instances with LLM-selected category descriptions. Extensive experiments demonstrate the superior performance of \MethodName over state-of-the-art models across diverse datasets, metrics, and supervision settings. Our code is available at https://github.com/amazon-science/Glean.