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

• URL: http://arxiv.org/abs/2502.18414v1
• Date: Tue, 25 Feb 2025 18:11:37 GMT
• Title: GLEAN: Generalized Category Discovery with Diverse and Quality-Enhanced LLM Feedback
• Authors: Henry Peng Zou, Siffi Singh, Yi Nian, Jianfeng He, Jason Cai, Saab Mansour, Hang Su,
• Abstract summary: Generalized Category Discovery (GCD) aims to recognize both known and novel categories in unlabeled data.<n>Previous GCD methods face significant challenges, such as difficulty in rectifying errors for confusing instances.<n>We propose GLEAN, a unified framework for generalized category discovery.
• Score: 13.969403782532957
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection [52.490375806093745]
  The objective of few-shot object detection (FSOD) is to detect novel objects with few training samples. We introduce the side information to alleviate the negative influences derived from the feature space and sample viewpoints. Our model outperforms the previous state-of-the-art methods, significantly improving the ability of FSOD in most shots/splits.
  arXiv  Detail & Related papers  (2025-04-09T17:24:05Z)
• CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection [22.6487590600505]
  We propose CQ-DINO, a category query-based object detection framework. CQ-DINO reformulates classification as a contrastive task between object queries and learnable category queries. Experiments demonstrate that CQ-DINO achieves superior performance on the challenging V3Det benchmark.
  arXiv  Detail & Related papers  (2025-03-24T08:22:55Z)
• Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery [10.98097145569408]
  Generalized Category Discovery (GCD) aims to classify unlabeled data containing both seen and novel categories. We propose incorporating part knowledge to address fine-grained GCD, which introduces two key challenges.
  arXiv  Detail & Related papers  (2025-03-21T01:37:51Z)
• Solving the Catastrophic Forgetting Problem in Generalized Category Discovery [46.63232918739251]
  Generalized Category Discovery (GCD) aims to identify a mix of known and novel categories within unlabeled data sets.<n>Recent state-of-the-art method SimGCD transfers the knowledge from known-class data to the learning of novel classes through debiased learning.<n>We propose a novel learning approach, LegoGCD, which is seamlessly integrated into previous methods to enhance the discrimination of novel classes.
  arXiv  Detail & Related papers  (2025-01-09T14:31:54Z)
• Active Generalized Category Discovery [60.69060965936214]
  Generalized Category Discovery (GCD) endeavors to cluster unlabeled samples from both novel and old classes. We take the spirit of active learning and propose a new setting called Active Generalized Category Discovery (AGCD) Our method achieves state-of-the-art performance on both generic and fine-grained datasets.
  arXiv  Detail & Related papers  (2024-03-07T07:12:24Z)
• Generalized Category Discovery with Large Language Models in the Loop [10.440661581492723]
  We propose Loop, an end-to-end active-learning framework that introduces Large Language Models into the training loop. We show that Loop outperforms SOTA models by a large margin and generates accurate category names for the discovered clusters.
  arXiv  Detail & Related papers  (2023-12-18T02:55:14Z)
• Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery [49.1865089933055]
  We propose a novel, efficient and self-supervised method capable of discovering previously unknown categories at test time. A salient feature of our approach is the assignment of minimum length category codes to individual data instances. Experimental evaluations, bolstered by state-of-the-art benchmark comparisons, testify to the efficacy of our solution.
  arXiv  Detail & Related papers  (2023-10-30T17:45:32Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Dynamic Conceptional Contrastive Learning for Generalized Category Discovery [76.82327473338734]
  Generalized category discovery (GCD) aims to automatically cluster partially labeled data. Unlabeled data contain instances that are not only from known categories of the labeled data but also from novel categories. One effective way for GCD is applying self-supervised learning to learn discriminate representation for unlabeled data. We propose a Dynamic Conceptional Contrastive Learning framework, which can effectively improve clustering accuracy.
  arXiv  Detail & Related papers  (2023-03-30T14:04:39Z)
• Open World Classification with Adaptive Negative Samples [89.2422451410507]
  Open world classification is a task in natural language processing with key practical relevance and impact. We propose an approach based on underlineadaptive underlinesamples (ANS) designed to generate effective synthetic open category samples in the training stage. ANS achieves significant improvements over state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-03-09T21:12:46Z)
• Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning [37.6512548064269]
  We investigate a new practical scenario called Fine-grained Category Discovery under Coarse-grained supervision (FCDC) FCDC aims at discovering fine-grained categories with only coarse-grained labeled data, which can adapt models to categories of different granularity from known ones and reduce significant labeling cost. We propose a hierarchical weighted self-contrastive network by building a novel weighted self-contrastive module and combining it with supervised learning in a hierarchical manner.
  arXiv  Detail & Related papers  (2022-10-14T12:06:23Z)
• Adaptive Class Suppression Loss for Long-Tail Object Detection [49.7273558444966]
  We devise a novel Adaptive Class Suppression Loss (ACSL) to improve the detection performance of tail categories. Our ACSL achieves 5.18% and 5.2% improvements with ResNet50-FPN, and sets a new state of the art.
  arXiv  Detail & Related papers  (2021-04-02T05:12:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.