Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery

• URL: http://arxiv.org/abs/2507.04051v1
• Date: Sat, 05 Jul 2025 14:20:49 GMT
• Title: Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery
• Authors: Xiao Liu, Nan Pu, Haiyang Zheng, Wenjing Li, Nicu Sebe, Zhun Zhong,
• Abstract summary: We investigate the online identification of newly arriving stream data that may belong to both known and unknown categories.<n>Existing OCD methods are devoted to fully mining transferable knowledge from only labeled data.<n>We propose a diffusion-based OCD framework, dubbed DiffGRE, which integrates attribute-composition generation, Refinement, and supervised recognition.
• Score: 64.83837781610907
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we investigate a practical yet challenging task: On-the-fly Category Discovery (OCD). This task focuses on the online identification of newly arriving stream data that may belong to both known and unknown categories, utilizing the category knowledge from only labeled data. Existing OCD methods are devoted to fully mining transferable knowledge from only labeled data. However, the transferability learned by these methods is limited because the knowledge contained in known categories is often insufficient, especially when few annotated data/categories are available in fine-grained recognition. To mitigate this limitation, we propose a diffusion-based OCD framework, dubbed DiffGRE, which integrates Generation, Refinement, and Encoding in a multi-stage fashion. Specifically, we first design an attribute-composition generation method based on cross-image interpolation in the diffusion latent space to synthesize novel samples. Then, we propose a diversity-driven refinement approach to select the synthesized images that differ from known categories for subsequent OCD model training. Finally, we leverage a semi-supervised leader encoding to inject additional category knowledge contained in synthesized data into the OCD models, which can benefit the discovery of both known and unknown categories during the on-the-fly inference process. Extensive experiments demonstrate the superiority of our DiffGRE over previous methods on six fine-grained datasets.

Related papers

• Freeze and Cluster: A Simple Baseline for Rehearsal-Free Continual Category Discovery [13.68907640197364]
  This paper addresses the problem of Rehearsal-Free Continual Category Discovery (RF-CCD)<n>RF-CCD focuses on continuously identifying novel class by leveraging knowledge from labeled data.<n>Previous approaches have struggled to effectively integrate advanced techniques from both domains.
  arXiv  Detail & Related papers  (2025-03-12T06:46:32Z)
• 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)
• Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery [65.16724941038052]
  Category-aware Prototype Generation (CPG) and Discrimi Category 5.3% (DCE) are proposed.<n>CPG enables the model to fully capture the intra-category diversity by representing each category with multiple prototypes.<n>DCE boosts the discrimination ability of hash code with the guidance of the generated category prototypes.
  arXiv  Detail & Related papers  (2024-10-24T23:51:40Z)
• Exclusive Style Removal for Cross Domain Novel Class Discovery [15.868889486516306]
  textitNovel Class Discovery (NCD) is usually a task to cluster unseen novel classes in an unlabeled set.<n>We introduce an exclusive style removal module for extracting style information that is distinctive from the baseline features.<n>This module is easy to integrate with other NCD methods, acting as a plug-in to improve performance on novel classes with different distributions.
  arXiv  Detail & Related papers  (2024-06-26T07:44:27Z)
• UniCell: Universal Cell Nucleus Classification via Prompt Learning [76.11864242047074]
  We propose a universal cell nucleus classification framework (UniCell) It employs a novel prompt learning mechanism to uniformly predict the corresponding categories of pathological images from different dataset domains. In particular, our framework adopts an end-to-end architecture for nuclei detection and classification, and utilizes flexible prediction heads for adapting various datasets.
  arXiv  Detail & Related papers  (2024-02-20T11:50:27Z)
• Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering [22.24175320515204]
  We propose a new novel class discovery framework for automatically discovering new semantic classes from dermoscopy image datasets. Specifically, we first use contrastive learning to learn a robust and unbiased feature representation based on all data from known and unknown categories. We conducted extensive experiments on the dermatology dataset ISIC 2019, and the experimental results show that our approach can effectively leverage knowledge from known categories to discover new semantic categories.
  arXiv  Detail & Related papers  (2023-09-28T13:59:29Z)
• 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)
• Class-incremental Novel Class Discovery [76.35226130521758]
  We study the new task of class-incremental Novel Class Discovery (class-iNCD) We propose a novel approach for class-iNCD which prevents forgetting of past information about the base classes. Our experiments, conducted on three common benchmarks, demonstrate that our method significantly outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-07-18T13:49:27Z)

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.