paper-with-me

Papers

GLEAN: Generalized Category Discovery with Diverse and Quality-Enhanced LLM Feedback

2025-02-25 · Henry Peng Zou, Siffi Singh, Yi Nian, Jianfeng He, Jason Cai, Saab Mansour, Hang Su

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.

📄 PDF Abstract BibTeX arXiv:2502.18414

Code (1)

amazon-science/Glean 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery

2024-07-26 · Fernando Julio Cendra, Bingchen Zhao, Kai Han

We tackle the problem of Continual Category Discovery (CCD), which aims to automatically discover novel categories in a continuous stream of unlabeled data while mitigating the challenge of catastrophic forgetting -- an …

Continual LearningRepresentation Learning

CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization

2026-09-09 · Luyao Tang, Jiewei Zheng, Kunze Huang, Chaoqi Chen 외 arxiv

Generalized Category Discovery (GCD) assigns unlabeled instances, mixed with labeled data, to known or novel categories, requiring human-like compositional reasoning: reusing primitives learned from known classes and dec…

Revisiting Mutual Information Maximization for Generalized Category Discovery

2024-05-31 · Zhaorui Tan, Chengrui Zhang, Xi Yang, Jie Sun 외

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 categories. This paper revisits the cha…

Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery

2025-07-07 · Jizhou Han, Shaokun Wang, Yuhang He, Chenhao Ding 외 arxiv

Generalized Category Discovery (GCD) focuses on classifying known categories while simultaneously discovering novel categories from unlabeled data. However, previous GCD methods face challenges due to inconsistent optimi…

ImbaGCD: Imbalanced Generalized Category Discovery

2023-12-04 · Ziyun Li, Ben Dai, Furkan Simsek, Christoph Meinel 외

Generalized class discovery (GCD) aims to infer known and unknown categories in an unlabeled dataset leveraging prior knowledge of a labeled set comprising known classes. Existing research implicitly/explicitly assumes t…