DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery

• URL: http://arxiv.org/abs/2504.04804v1
• Date: Mon, 07 Apr 2025 07:56:01 GMT
• Title: DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery
• Authors: Yuanpei Liu, Kai Han,
• Abstract summary: We tackle the problem of Generalized Category Discovery (GCD)<n>In GCD, an inherent label bias exists between known and unknown classes due to the lack of ground-truth labels for the latter.<n>We introduce DebGCD, a underlineDebiased learning with distribution guidance framework for underlineGCD.
• Score: 14.222473509173357
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In this paper, we tackle the problem of Generalized Category Discovery (GCD). Given a dataset containing both labelled and unlabelled images, the objective is to categorize all images in the unlabelled subset, irrespective of whether they are from known or unknown classes. In GCD, an inherent label bias exists between known and unknown classes due to the lack of ground-truth labels for the latter. State-of-the-art methods in GCD leverage parametric classifiers trained through self-distillation with soft labels, leaving the bias issue unattended. Besides, they treat all unlabelled samples uniformly, neglecting variations in certainty levels and resulting in suboptimal learning. Moreover, the explicit identification of semantic distribution shifts between known and unknown classes, a vital aspect for effective GCD, has been neglected. To address these challenges, we introduce DebGCD, a \underline{Deb}iased learning with distribution guidance framework for \underline{GCD}. Initially, DebGCD co-trains an auxiliary debiased classifier in the same feature space as the GCD classifier, progressively enhancing the GCD features. Moreover, we introduce a semantic distribution detector in a separate feature space to implicitly boost the learning efficacy of GCD. Additionally, we employ a curriculum learning strategy based on semantic distribution certainty to steer the debiased learning at an optimized pace. Thorough evaluations on GCD benchmarks demonstrate the consistent state-of-the-art performance of our framework, highlighting its superiority. Project page: https://visual-ai.github.io/debgcd/

Related papers

• Hyperbolic Category Discovery [12.654574453480635]
  Generalized Category Discovery (GCD) aims to categorize all images in the unlabelled subset, regardless of whether they belong to known or unknown classes. Hyperbolic framework for learning hierarchy-aware representations and classifiers for GCD is presented.
  arXiv  Detail & Related papers  (2025-04-08T15:12:33Z)
• ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery [42.965641047139904]
  Generalized category discovery (GCD) is a pragmatic but underexplored problem. Unlabeled data contain both old and new classes. ProtoGCD achieves state-of-the-art performance on both generic and fine-grained datasets.
  arXiv  Detail & Related papers  (2025-04-02T06:13:14Z)
• Generalized Class Discovery in Instance Segmentation [7.400926717561454]
  We propose an instance-wise temperature assignment (ITA) method for contrastive learning and class-wise reliability criteria for pseudo-labels.<n>We evaluate our proposed method by conducting experiments on two settings: COCO$_half$ + LVIS and LVIS + Visual Genome.
  arXiv  Detail & Related papers  (2025-02-12T06:26:05Z)
• Happy: A Debiased Learning Framework for Continual Generalized Category Discovery [54.54153155039062]
  This paper explores the underexplored task of Continual Generalized Category Discovery (C-GCD) C-GCD aims to incrementally discover new classes from unlabeled data while maintaining the ability to recognize previously learned classes. We introduce a debiased learning framework, namely Happy, characterized by Hardness-aware prototype sampling and soft entropy regularization.
  arXiv  Detail & Related papers  (2024-10-09T04:18:51Z)
• 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)
• ImbaGCD: Imbalanced Generalized Category Discovery [8.905027373521213]
  Generalized class discovery (GCD) aims to infer known and unknown categories in an unlabeled dataset. In nature, we are more likely to encounter known/common classes than unknown/uncommon ones. We present ImbaGCD, a novel optimal transport-based expectation framework that accomplishes generalized category discovery.
  arXiv  Detail & Related papers  (2023-12-04T09:46:09Z)
• GeT: Generative Target Structure Debiasing for Domain Adaptation [67.17025068995835]
  Domain adaptation (DA) aims to transfer knowledge from a fully labeled source to a scarcely labeled or totally unlabeled target under domain shift. Recently, semi-supervised learning-based (SSL) techniques that leverage pseudo labeling have been increasingly used in DA. In this paper, we propose GeT that learns a non-bias target embedding distribution with high quality pseudo labels.
  arXiv  Detail & Related papers  (2023-08-20T08:52:43Z)
• OpenGCD: Assisting Open World Recognition with Generalized Category Discovery [4.600906853436266]
  A desirable open world recognition (OWR) system requires performing three tasks. We propose OpenGCD that combines three key ideas to solve the above problems sequentially. Experiments on two standard classification benchmarks and a challenging dataset demonstrate that OpenGCD not only offers excellent compatibility but also substantially outperforms other baselines.
  arXiv  Detail & Related papers  (2023-08-14T04:10:45Z)
• Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery [36.01459228175808]
  We propose an EM-like framework that alternates between representation learning and class number estimation. We evaluate our framework on both generic image classification datasets and challenging fine-grained object recognition datasets.
  arXiv  Detail & Related papers  (2023-05-10T13:47:38Z)
• 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)
• Parametric Classification for Generalized Category Discovery: A Baseline Study [70.73212959385387]
  Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. We investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers.
  arXiv  Detail & Related papers  (2022-11-21T18:47:11Z)
• Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification [64.37745443119942]
  This paper jointly enforces visual and temporal consistency in the combination of a local one-hot classification and a global multi-class classification. Experimental results on three large-scale ReID datasets demonstrate the superiority of proposed method in both unsupervised and unsupervised domain adaptive ReID tasks.
  arXiv  Detail & Related papers  (2020-07-21T14:31:27Z)

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.