paper-with-me

홈 › Papers

Invariant Representation via Decoupling Style and Spurious Features from Images

2023-12-11 · Ruimeng Li, Yuanhao Pu, Zhaoyi Li, Hong Xie, Defu Lian

This paper considers the out-of-distribution (OOD) generalization problem under the setting that both style distribution shift and spurious features exist and domain labels are missing. This setting frequently arises in real-world applications and is underlooked because previous approaches mainly handle either of these two factors. The critical challenge is decoupling style and spurious features in the absence of domain labels. To address this challenge, we first propose a structural causal model (SCM) for the image generation process, which captures both style distribution shift and spurious features. The proposed SCM enables us to design a new framework called IRSS, which can gradually separate style distribution and spurious features from images by introducing adversarial neural networks and multi-environment optimization, thus achieving OOD generalization. Moreover, it does not require additional supervision (e.g., domain labels) other than the images and their corresponding labels. Experiments on benchmark datasets demonstrate that IRSS outperforms traditional OOD methods and solves the problem of Invariant risk minimization (IRM) degradation, enabling the extraction of invariant features under distribution shift.

📄 PDF Abstract BibTeX arXiv:2312.06226

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationRepresentation Learning

Similar Papers 제목 키워드 기반

Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective

2021-11-29 · CVPR 2022 1 · Yuejiang Liu, Riccardo Cadei, Jonas Schweizer, Sherwin Bahmani 외

Learning behavioral patterns from observational data has been a de-facto approach to motion forecasting. Yet, the current paradigm suffers from two shortcomings: brittle under distribution shifts and inefficient for know…

Motion ForecastingOut-of-Distribution GeneralizationTransfer Learning

Let Samples Speak: Mitigating Spurious Correlation by Exploiting the Clusterness of Samples

2025-12-28 · Weiwei Li, Junzhuo Liu, Yuanyuan Ren, Yuchen Zheng 외 arxiv

Deep learning models are known to often learn features that spuriously correlate with the class label during training but are irrelevant to the prediction task. Existing methods typically address this issue by annotating…

Let Samples Speak: Mitigating Spurious Correlation by Exploiting the Clusterness of Samples

2025-01-01 · CVPR 2025 1 · Weiwei Li, Junzhuo Liu, Yuanyuan Ren, Yuchen Zheng 외

Deep learning models are known to often learn features that spuriously correlate with the class label during training but are irrelevant to the prediction task. Existing methods typically address this issue by annota…

Conditional entropy minimization principle for learning domain invariant representation features

2022-01-25 · Thuan Nguyen, Boyang Lyu, Prakash Ishwar, Matthias Scheutz 외

Invariance-principle-based methods such as Invariant Risk Minimization (IRM), have recently emerged as promising approaches for Domain Generalization (DG). Despite promising theory, such approaches fail in common classif…

Domain Generalization

Distributionally Robust Optimization and Invariant Representation Learning for Addressing Subgroup Underrepresentation: Mechanisms and Limitations

2023-08-12 · Nilesh Kumar, Ruby Shrestha, Zhiyuan Li, Linwei Wang

Spurious correlation caused by subgroup underrepresentation has received increasing attention as a source of bias that can be perpetuated by deep neural networks (DNNs). Distributionally robust optimization has shown suc…

image-classificationImage ClassificationMedical Image ClassificationRepresentation Learning