Generative Classifier for Domain Generalization

• URL: http://arxiv.org/abs/2504.02272v1
• Date: Thu, 03 Apr 2025 04:38:33 GMT
• Title: Generative Classifier for Domain Generalization
• Authors: Shaocong Long, Qianyu Zhou, Xiangtai Li, Chenhao Ying, Yunhai Tong, Lizhuang Ma, Yuan Luo, Dacheng Tao,
• Abstract summary: Domain generalization aims to the generalizability of computer vision models toward distribution shifts.<n>We propose Generative-driven Domain Generalization (GCDG)<n>GCDG consists of three key modules: Heterogeneity Learning(HLC), Spurious Correlation(SCB), and Diverse Component Balancing(DCB)
• Score: 84.92088101715116
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods focus on learning domain invariance, however, such methods overlook the potential inherent in domain-specific information. While the prevailing practice of discriminative linear classifier has been tailored to domain-invariant features, it struggles when confronted with diverse domain-specific information, e.g., intra-class shifts, that exhibits multi-modality. To address these issues, we explore the theoretical implications of relying on domain invariance, revealing the crucial role of domain-specific information in mitigating the target risk for DG. Drawing from these insights, we propose Generative Classifier-driven Domain Generalization (GCDG), introducing a generative paradigm for the DG classifier based on Gaussian Mixture Models (GMMs) for each class across domains. GCDG consists of three key modules: Heterogeneity Learning Classifier~(HLC), Spurious Correlation Blocking~(SCB), and Diverse Component Balancing~(DCB). Concretely, HLC attempts to model the feature distributions and thereby capture valuable domain-specific information via GMMs. SCB identifies the neural units containing spurious correlations and perturbs them, mitigating the risk of HLC learning spurious patterns. Meanwhile, DCB ensures a balanced contribution of components in HLC, preventing the underestimation or neglect of critical components. In this way, GCDG excels in capturing the nuances of domain-specific information characterized by diverse distributions. GCDG demonstrates the potential to reduce the target risk and encourage flat minima, improving the generalizability. Extensive experiments show GCDG's comparable performance on five DG benchmarks and one face anti-spoofing dataset, seamlessly integrating into existing DG methods with consistent improvements.

Related papers

• Domain Generalization via Discrete Codebook Learning [30.169237668528947]
  Domain generalization (DG) strives to address distribution shifts across diverse environments to enhance model's generalizability. We introduce a novel learning paradigm for DG, termed Domain Generalization (DDG) DDG proposes to use a codebook to quantize the feature map into discrete codewords, aligning semantic-equivalent information in a shared representation space.
  arXiv  Detail & Related papers  (2025-04-09T04:19:35Z)
• Disentangling Masked Autoencoders for Unsupervised Domain Generalization [57.56744870106124]
  Unsupervised domain generalization is fast gaining attention but is still far from well-studied. Disentangled Masked Auto (DisMAE) aims to discover the disentangled representations that faithfully reveal intrinsic features. DisMAE co-trains the asymmetric dual-branch architecture with semantic and lightweight variation encoders.
  arXiv  Detail & Related papers  (2024-07-10T11:11:36Z)
• PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization [24.413415998529754]
  We propose a new benchmark Hybrid Domain Generalization (HDG) and a novel metric $H2$-CV, which construct various splits to assess the robustness of algorithms. Our method outperforms state-of-the-art algorithms on multiple datasets, especially improving the robustness when confronting data scarcity.
  arXiv  Detail & Related papers  (2024-04-13T13:41:13Z)
• Towards Domain-Specific Features Disentanglement for Domain Generalization [23.13095840134744]
  We propose a novel contrastive-based disentanglement method CDDG to exploit the over-looked domain-specific features. Specifically, CDDG learns to decouple inherent mutually exclusive features by leveraging them in the latent space. Experiments conducted on various benchmark datasets demonstrate the superiority of our method compared to other state-of-the-art approaches.
  arXiv  Detail & Related papers  (2023-10-04T17:51:02Z)
• Diverse Target and Contribution Scheduling for Domain Generalization [31.967801550742312]
  Generalization under the distribution shift has been a great challenge in computer vision. We propose a new paradigm for DG called Diverse Target and Contribution Scheduling (DTCS) DTCS comprises two innovative modules: Diverse Target Supervision (DTS) and Diverse Contribution Balance (DCB)
  arXiv  Detail & Related papers  (2023-09-28T14:10:25Z)
• Consistency Regularization for Domain Generalization with Logit Attribution Matching [14.98337914353095]
  Domain generalization (DG) is about training models that generalize well under domain shift. We consider a third, lesser-known setting where a training domain is endowed with a collection of pairs of examples that share the same semantic information. We present a theory showing consistency regularization is conducive to DG and propose a novel CR method called Logit Matching.
  arXiv  Detail & Related papers  (2023-05-13T10:21:53Z)
• Adaptive Domain Generalization via Online Disagreement Minimization [17.215683606365445]
  Domain Generalization aims to safely transfer a model to unseen target domains. AdaODM adaptively modifies the source model at test time for different target domains. Results show AdaODM stably improves the generalization capacity on unseen domains.
  arXiv  Detail & Related papers  (2022-08-03T11:51:11Z)
• On Certifying and Improving Generalization to Unseen Domains [87.00662852876177]
  Domain Generalization aims to learn models whose performance remains high on unseen domains encountered at test-time. It is challenging to evaluate DG algorithms comprehensively using a few benchmark datasets. We propose a universal certification framework that can efficiently certify the worst-case performance of any DG method.
  arXiv  Detail & Related papers  (2022-06-24T16:29:43Z)
• Compound Domain Generalization via Meta-Knowledge Encoding [55.22920476224671]
  We introduce Style-induced Domain-specific Normalization (SDNorm) to re-normalize the multi-modal underlying distributions. We harness the prototype representations, the centroids of classes, to perform relational modeling in the embedding space. Experiments on four standard Domain Generalization benchmarks reveal that COMEN exceeds the state-of-the-art performance without the need of domain supervision.
  arXiv  Detail & Related papers  (2022-03-24T11:54:59Z)
• 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)
• Dual Distribution Alignment Network for Generalizable Person Re-Identification [174.36157174951603]
  Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID) We present a Dual Distribution Alignment Network (DDAN) which handles this challenge by selectively aligning distributions of multiple source domains. We evaluate our DDAN on a large-scale Domain Generalization Re-ID (DG Re-ID) benchmark.
  arXiv  Detail & Related papers  (2020-07-27T00:08:07Z)

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.