Casual Inference via Style Bias Deconfounding for Domain Generalization

• URL: http://arxiv.org/abs/2503.16852v1
• Date: Fri, 21 Mar 2025 04:52:31 GMT
• Title: Casual Inference via Style Bias Deconfounding for Domain Generalization
• Authors: Jiaxi Li, Di Lin, Hao Chen, Hongying Liu, Liang Wan, Wei Feng,
• Abstract summary: We introduce Style Deconfounding Causal Learning, a novel causal inference-based framework designed to explicitly address style as a confounding factor.<n>Our approaches begin with constructing a structural causal model (SCM) tailored to the domain generalization problem and applies a backdoor adjustment strategy to account for style influence.<n>Building on this foundation, we design a style-guided expert module (SGEM) to adaptively clusters style distributions during training, capturing the global confounding style.<n>A back-door causal learning module (BDCL) performs causal interventions during feature extraction, ensuring fair integration of global confounding styles into sample predictions, effectively reducing style bias
• Score: 28.866189619091227
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks (DNNs) often struggle with out-of-distribution data, limiting their reliability in diverse realworld applications. To address this issue, domain generalization methods have been developed to learn domain-invariant features from single or multiple training domains, enabling generalization to unseen testing domains. However, existing approaches usually overlook the impact of style frequency within the training set. This oversight predisposes models to capture spurious visual correlations caused by style confounding factors, rather than learning truly causal representations, thereby undermining inference reliability. In this work, we introduce Style Deconfounding Causal Learning (SDCL), a novel causal inference-based framework designed to explicitly address style as a confounding factor. Our approaches begins with constructing a structural causal model (SCM) tailored to the domain generalization problem and applies a backdoor adjustment strategy to account for style influence. Building on this foundation, we design a style-guided expert module (SGEM) to adaptively clusters style distributions during training, capturing the global confounding style. Additionally, a back-door causal learning module (BDCL) performs causal interventions during feature extraction, ensuring fair integration of global confounding styles into sample predictions, effectively reducing style bias. The SDCL framework is highly versatile and can be seamlessly integrated with state-of-the-art data augmentation techniques. Extensive experiments across diverse natural and medical image recognition tasks validate its efficacy, demonstrating superior performance in both multi-domain and the more challenging single-domain generalization scenarios.

Related papers

• Object Style Diffusion for Generalized Object Detection in Urban Scene [69.04189353993907]
  We introduce a novel single-domain object detection generalization method, named GoDiff. By integrating pseudo-target domain data with source domain data, we diversify the training dataset. Experimental results demonstrate that our method not only enhances the generalization ability of existing detectors but also functions as a plug-and-play enhancement for other single-domain generalization methods.
  arXiv  Detail & Related papers  (2024-12-18T13:03:00Z)
• Cross-Domain Continual Learning via CLAMP [10.553456651003055]
  CLAMP significantly outperforms established baseline algorithms across all experiments by at least $10%$ margin. An assessor-guided learning process is put forward to navigate the learning process of a base model.
  arXiv  Detail & Related papers  (2024-05-12T02:41:31Z)
• DIGIC: Domain Generalizable Imitation Learning by Causal Discovery [69.13526582209165]
  Causality has been combined with machine learning to produce robust representations for domain generalization. We make a different attempt by leveraging the demonstration data distribution to discover causal features for a domain generalizable policy. We design a novel framework, called DIGIC, to identify the causal features by finding the direct cause of the expert action from the demonstration data distribution.
  arXiv  Detail & Related papers  (2024-02-29T07:09:01Z)
• A Novel Cross-Perturbation for Single Domain Generalization [54.612933105967606]
  Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain. The limited diversity in the training data hampers the learning of domain-invariant features, resulting in compromised generalization performance. We propose CPerb, a simple yet effective cross-perturbation method to enhance the diversity of the training data.
  arXiv  Detail & Related papers  (2023-08-02T03:16:12Z)
• FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation [23.0771949978506]
  Existing skeleton-based action recognition methods typically follow a centralized learning paradigm, which can pose privacy concerns when exposing human-related videos. We introduce a novel Federated Skeleton-based Action Recognition (FSAR) paradigm, which enables the construction of a globally generalized model without accessing local sensitive data.
  arXiv  Detail & Related papers  (2023-06-19T16:18:14Z)
• Randomized Adversarial Style Perturbations for Domain Generalization [49.888364462991234]
  We propose a novel domain generalization technique, referred to as Randomized Adversarial Style Perturbation (RASP) The proposed algorithm perturbs the style of a feature in an adversarial direction towards a randomly selected class, and makes the model learn against being misled by the unexpected styles observed in unseen target domains. We evaluate the proposed algorithm via extensive experiments on various benchmarks and show that our approach improves domain generalization performance, especially in large-scale benchmarks.
  arXiv  Detail & Related papers  (2023-04-04T17:07:06Z)
• Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization [113.03189252044773]
  We propose a unified framework, Style-HAllucinated Dual consistEncy learning (SHADE), to handle domain shift in various visual tasks. Our versatile SHADE can significantly enhance the generalization in various visual recognition tasks, including image classification, semantic segmentation and object detection.
  arXiv  Detail & Related papers  (2022-12-18T11:42:51Z)
• Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts [133.99270341855728]
  Real-world domain styles can vary substantially due to environment changes and sensor noises. Deep models only know the training domain style. We propose Normalization Perturbation to overcome this domain style overfitting problem.
  arXiv  Detail & Related papers  (2022-11-08T17:36:49Z)

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.