paper-with-me

홈 › Papers

Out-of-distribution Generalization via Partial Feature Decorrelation

2020-07-30 · Xin Guo, Zhengxu Yu, Chao Xiang, Zhongming Jin, Jianqiang Huang, Deng Cai, Xiaofei He, Xian-Sheng Hua

Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting. However, out-of-distribution (OOD) generalization is more common in practice, which means an agnostic context distribution shift between training and testing environments. To address this problem, we present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimizes a feature decomposition network and the target image classification model. The feature decomposition network decomposes feature embeddings into the independent and the correlated parts such that the correlations between features will be highlighted. Then, the correlated features help learn a stable feature representation by decorrelating the highlighted correlations while optimizing the image classification model. We verify the correlation modeling ability of the feature decomposition network on a synthetic dataset. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.

📄 PDF Abstract BibTeX arXiv:2007.15241

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral Classificationimage-classificationImage ClassificationOut-of-Distribution GeneralizationRepresentation Learning

Similar Papers 제목 키워드 기반

Factor Decorrelation Enhanced Data Removal from Deep Predictive Models

2025-09-27 · Wenhao Yang, Lin Li, Xiaohui Tao, Kaize Shi arxiv

The imperative of user privacy protection and regulatory compliance necessitates sensitive data removal in model training, yet this process often induces distributional shifts that undermine model performance-particularl…

Rule Learning for Knowledge Graph Reasoning under Agnostic Distribution Shift

2025-07-07 · Shixuan Liu, Yue He, Yunfei Wang, Hao Zou 외 arxiv

Logical rule learning, a prominent category of knowledge graph (KG) reasoning methods, constitutes a critical research area aimed at learning explicit rules from observed facts to infer missing knowledge. However, like a…

Robust Multimodal Representation Learning in Healthcare

2026-01-29 · Xiaoguang Zhu, Linxiao Gong, Lianlong Sun, Yang Liu 외 arxiv

Medical multimodal representation learning aims to integrate heterogeneous data into unified patient representations to support clinical outcome prediction. However, real-world medical datasets commonly contain systemati…

Representation Learning

Learning to Reweight for Graph Neural Network

2023-12-19 · Zhengyu Chen, Teng Xiao, Kun Kuang, Zheqi Lv 외

Graph Neural Networks (GNNs) show promising results for graph tasks. However, existing GNNs' generalization ability will degrade when there exist distribution shifts between testing and training graph data. The cardinal …

Graph Neural NetworkOut-of-Distribution Generalization

Distribution Shift Aware Neural Tabular Learning

2025-08-27 · Wangyang Ying, Nanxu Gong, Dongjie Wang, Xinyuan Wang 외 arxiv

Tabular learning transforms raw features into optimized spaces for downstream tasks, but its effectiveness deteriorates under distribution shifts between training and testing data. We formalize this challenge as the Dist…