Unleashing the Power of Neural Collapse: Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery

• URL: http://arxiv.org/abs/2507.04725v1
• Date: Mon, 07 Jul 2025 07:34:41 GMT
• Title: Unleashing the Power of Neural Collapse: Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery
• Authors: Jizhou Han, Shaokun Wang, Yuhang He, Chenhao Ding, Qiang Wang, Xinyuan Gao, SongLin Dong, Yihong Gong,
• Abstract summary: Generalized Category Discovery (GCD) focuses on classifying known categories while simultaneously discovering novel categories from unlabeled data.<n>Previous GCD methods face challenges due to inconsistent optimization objectives and category confusion.<n>We propose the Neural Collapse-inspired Generalized Category Discovery (NC-GCD) framework.
• Score: 19.872346734645383
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 optimization objectives and category confusion. This leads to feature overlap and ultimately hinders performance on novel categories. To address these issues, we propose the Neural Collapse-inspired Generalized Category Discovery (NC-GCD) framework. By pre-assigning and fixing Equiangular Tight Frame (ETF) prototypes, our method ensures an optimal geometric structure and a consistent optimization objective for both known and novel categories. We introduce a Consistent ETF Alignment Loss that unifies supervised and unsupervised ETF alignment and enhances category separability. Additionally, a Semantic Consistency Matcher (SCM) is designed to maintain stable and consistent label assignments across clustering iterations. Our method achieves strong performance on multiple GCD benchmarks, significantly enhancing novel category accuracy and demonstrating its effectiveness.

Related papers

• Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs [34.06878654462158]
  We introduce Event-Centric GCD, characterized by long, complex narratives and highly imbalanced class distributions.<n>We propose PaMA, a framework leveraging LLMs to extract and refine event patterns for improved cluster-class alignment.<n> Evaluations on two EC-GCD benchmarks, including a newly constructed Scam Report dataset, demonstrate that PaMA outperforms prior methods with up to 12.58% H-score gains.
  arXiv  Detail & Related papers  (2025-05-29T10:02:04Z)
• A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization [83.12938977698988]
  Generalized Category Discovery (GCD) aims to classify both base and novel images using labeled base data. Current approaches inadequately address the intrinsic optimization of the co-occurrence matrix $barA$ based on cosine similarity. We propose a Non-Negative Generalized Category Discovery (NN-GCD) framework to address these deficiencies.
  arXiv  Detail & Related papers  (2024-10-29T07:24:11Z)
• NC-NCD: Novel Class Discovery for Node Classification [28.308556235456766]
  Class Discovery (NCD) involves identifying new categories within unlabeled data by utilizing knowledge acquired from previously established categories. Existing NCD methods often struggle to maintain a balance between the performance of old and new categories. We introduce for the first time a more practical NCD scenario for node classification (i.e., NC-NCD) We propose a novel self-training framework with prototype replay and distillation called SWORD, adopted to our NC-NCD setting.
  arXiv  Detail & Related papers  (2024-07-25T07:10:08Z)
• OMH: Structured Sparsity via Optimally Matched Hierarchy for Unsupervised Semantic Segmentation [69.37484603556307]
  Un Semantic segmenting (USS) involves segmenting images without relying on predefined labels. We introduce a novel approach called Optimally Matched Hierarchy (OMH) to simultaneously address the above issues. Our OMH yields better unsupervised segmentation performance compared to existing USS methods.
  arXiv  Detail & Related papers  (2024-03-11T09:46:41Z)
• 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)
• Balanced Classification: A Unified Framework for Long-Tailed Object Detection [74.94216414011326]
  Conventional detectors suffer from performance degradation when dealing with long-tailed data due to a classification bias towards the majority head categories. We introduce a unified framework called BAlanced CLassification (BACL), which enables adaptive rectification of inequalities caused by disparities in category distribution. BACL consistently achieves performance improvements across various datasets with different backbones and architectures.
  arXiv  Detail & Related papers  (2023-08-04T09:11:07Z)
• 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)
• Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering [119.88565565454378]
  Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain. We propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one. Our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings.
  arXiv  Detail & Related papers  (2020-12-08T08:52:00Z)
• TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples [25.68199820110267]
  We propose a Target-Oriented Alignment Network (TOAN) to investigate the fine-grained relation between the target query image and support classes. The feature of each support image is transformed to match the query ones in the embedding feature space, which reduces the disparity explicitly within each category.
  arXiv  Detail & Related papers  (2020-05-28T07:48:44Z)

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.