paper-with-me

홈 › Papers

Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations

2024-01-11 · Na Wang, Lei Qi, Jintao Guo, Yinghuan Shi, Yang Gao

Domain generalization (DG) intends to train a model on multiple source domains to ensure that it can generalize well to an arbitrary unseen target domain. The acquisition of domain-invariant representations is pivotal for DG as they possess the ability to capture the inherent semantic information of the data, mitigate the influence of domain shift, and enhance the generalization capability of the model. Adopting multiple perspectives, such as the sample and the feature, proves to be effective. The sample perspective facilitates data augmentation through data manipulation techniques, whereas the feature perspective enables the extraction of meaningful generalization features. In this paper, we focus on improving the generalization ability of the model by compelling it to acquire domain-invariant representations from both the sample and feature perspectives by disentangling spurious correlations and enhancing potential correlations. 1) From the sample perspective, we develop a frequency restriction module, guiding the model to focus on the relevant correlations between object features and labels, thereby disentangling spurious correlations. 2) From the feature perspective, the simple Tail Interaction module implicitly enhances potential correlations among all samples from all source domains, facilitating the acquisition of domain-invariant representations across multiple domains for the model. The experimental results show that Convolutional Neural Networks (CNNs) or Multi-Layer Perceptrons (MLPs) with a strong baseline embedded with these two modules can achieve superior results, e.g., an average accuracy of 92.30% on Digits-DG.

📄 PDF Abstract BibTeX arXiv:2401.05752

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDomain Generalization

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Disentangling Causal Substructures for Interpretable and Generalizable Drug Synergy Prediction

2025-11-04 · Yi Luo, Haochen Zhao, Xiao Liang, Yiwei Liu 외 arxiv

Drug synergy prediction is a critical task in the development of effective combination therapies for complex diseases, including cancer. Although existing methods have shown promising results, they often operate as black…

Drug Discovery

MIMM-X: Disentangling Spurious Correlations for Medical Image Analysis

2025-11-28 · Louisa Fay, Hajer Reguigui, Bin Yang, Sergios Gatidis 외 arxiv

Deep learning models can excel on medical tasks, yet often experience spurious correlations, known as shortcut learning, leading to poor generalization in new environments. Particularly in medical imaging, where multiple…

Controllable Relation Disentanglement for Few-Shot Class-Incremental Learning

2024-03-17 · Yuan Zhou, Richang Hong, Yanrong Guo, Lin Liu 외

In this paper, we propose to tackle Few-Shot Class-Incremental Learning (FSCIL) from a new perspective, i.e., relation disentanglement, which means enhancing FSCIL via disentangling spurious relation between categories. …

class-incremental learningClass Incremental LearningDisentanglementFew-Shot Class-Incremental Learning+2

Identifying and Disentangling Spurious Features in Pretrained Image Representations

2023-06-22 · Rafayel Darbinyan, Hrayr Harutyunyan, Aram H. Markosyan, Hrant Khachatrian

Neural networks employ spurious correlations in their predictions, resulting in decreased performance when these correlations do not hold. Recent works suggest fixing pretrained representations and training a classificat…

Debiasing Counterfactuals In the Presence of Spurious Correlations

2023-08-21 · Amar Kumar, Nima Fathi, Raghav Mehta, Brennan Nichyporuk 외

Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correlations (i.e. confounders), should they be prevalent in the training dataset, rat…

counterfactualImage Generation