Long-Tailed Learning for Generalized Category Discovery

• URL: http://arxiv.org/abs/2506.06965v1
• Date: Sun, 08 Jun 2025 02:01:49 GMT
• Title: Long-Tailed Learning for Generalized Category Discovery
• Authors: Cuong Manh Hoang,
• Abstract summary: We propose a novel framework that performs generalized category discovery in long-tailed distributions.<n>We first present a self-guided labeling technique that uses a learnable distribution to generate pseudo-labels.<n>We then introduce a representation balancing process to derive discriminative representations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generalized Category Discovery (GCD) utilizes labeled samples of known classes to discover novel classes in unlabeled samples. Existing methods show effective performance on artificial datasets with balanced distributions. However, real-world datasets are always imbalanced, significantly affecting the effectiveness of these methods. To solve this problem, we propose a novel framework that performs generalized category discovery in long-tailed distributions. We first present a self-guided labeling technique that uses a learnable distribution to generate pseudo-labels, resulting in less biased classifiers. We then introduce a representation balancing process to derive discriminative representations. By mining sample neighborhoods, this process encourages the model to focus more on tail classes. We conduct experiments on public datasets to demonstrate the effectiveness of the proposed framework. The results show that our model exceeds previous state-of-the-art methods.

Related papers

• CVOCSemRPL: Class-Variance Optimized Clustering, Semantic Information Injection and Restricted Pseudo Labeling based Improved Semi-Supervised Few-Shot Learning [4.3149314441871205]
  In the semi-supervised few-shot learning setting, substantial quantities of unlabeled samples are available.<n>Such unlabeled samples are generally cheaper to obtain and can be used to improve the few-shot learning performance of the model.<n>In this paper, we focus on improving the representation learned by the model in order to improve the clustering and, consequently, the model performance.
  arXiv  Detail & Related papers  (2025-01-24T11:14:35Z)
• Data Pruning in Generative Diffusion Models [2.0111637969968]
  Generative models aim to estimate the underlying distribution of the data, so presumably they should benefit from larger datasets.<n>We show that eliminating redundant or noisy data in large datasets is beneficial particularly when done strategically.
  arXiv  Detail & Related papers  (2024-11-19T14:13:25Z)
• Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition [50.61991746981703]
  Current state-of-the-art LTSSL approaches rely on high-quality pseudo-labels for large-scale unlabeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels.
  arXiv  Detail & Related papers  (2024-10-08T15:06:10Z)
• Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification [49.09505771145326]
  We propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
  arXiv  Detail & Related papers  (2024-04-26T06:00:27Z)
• Class-Balancing Diffusion Models [57.38599989220613]
  Class-Balancing Diffusion Models (CBDM) are trained with a distribution adjustment regularizer as a solution. Our method benchmarked the generation results on CIFAR100/CIFAR100LT dataset and shows outstanding performance on the downstream recognition task.
  arXiv  Detail & Related papers  (2023-04-30T20:00:14Z)
• Diffusing Gaussian Mixtures for Generating Categorical Data [21.43283907118157]
  We propose a generative model for categorical data based on diffusion models with a focus on high-quality sample generation. Our method of evaluation highlights the capabilities and limitations of different generative models for generating categorical data.
  arXiv  Detail & Related papers  (2023-03-08T14:55:32Z)
• Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
  Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data. We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
  arXiv  Detail & Related papers  (2023-03-06T14:49:59Z)
• Combining Self-labeling with Selective Sampling [2.0305676256390934]
  This work combines self-labeling techniques with active learning in a selective sampling scenario. We show that naive application of self-labeling can harm performance by introducing bias towards selected classes. The proposed method matches current selective sampling methods or achieves better results.
  arXiv  Detail & Related papers  (2023-01-11T11:58:45Z)
• 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)
• Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets [24.551465814633325]
  Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance. Recent studies found that directly training with out-of-distribution data in a semi-supervised manner would harm the generalization performance. We propose a novel method called Open-sampling, which utilizes open-set noisy labels to re-balance the class priors of the training dataset.
  arXiv  Detail & Related papers  (2022-06-17T14:29:52Z)
• Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
  We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers. We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model. Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
  arXiv  Detail & Related papers  (2020-06-22T21:12:31Z)

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.