paper-with-me

홈 › Papers

Unsupervised Learning of Debiased Representations with Pseudo-Attributes

2021-08-06 · CVPR 2022 1 · Seonguk Seo, Joon-Young Lee, Bohyung Han

Dataset bias is a critical challenge in machine learning since it often leads to a negative impact on a model due to the unintended decision rules captured by spurious correlations. Although existing works often handle this issue based on human supervision, the availability of the proper annotations is impractical and even unrealistic. To better tackle the limitation, we propose a simple but effective unsupervised debiasing technique. Specifically, we first identify pseudo-attributes based on the results from clustering performed in the feature embedding space even without an explicit bias attribute supervision. Then, we employ a novel cluster-wise reweighting scheme to learn debiased representation; the proposed method prevents minority groups from being discounted for minimizing the overall loss, which is desirable for worst-case generalization. The extensive experiments demonstrate the outstanding performance of our approach on multiple standard benchmarks, even achieving the competitive accuracy to the supervised counterpart.

📄 PDF Abstract BibTeX arXiv:2108.02943

Code (1)

skynbe/pseudo-attributes pytorch

Tasks

Attribute

Similar Papers 제목 키워드 기반

Learning Debiased Representations via Conditional Attribute Interpolation

2023-01-01 · CVPR 2023 1 · Yi-Kai Zhang, Qi-Wei Wang, De-Chuan Zhan, Han-Jia Ye

An image is usually described by more than one attribute like "shape" and "color". When a dataset is biased, i.e., most samples have attributes spuriously correlated with the target label, a Deep Neural Network (DNN)…

AttributeMetric Learning

Debiased Learning from Naturally Imbalanced Pseudo-Labels

2022-01-05 · CVPR 2022 1 · Xudong Wang, Zhirong Wu, Long Lian, Stella X. Yu

Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setti…

counterfactualCounterfactual ReasoningFew-Shot Image Classificationimbalanced classification+2

Learning by Imagining: Debiased Feature Augmentation for Compositional Zero-Shot Learning

2025-09-16 · Haozhe Zhang, Chenchen Jing, Mingyu Liu, Qingsheng Wang 외 arxiv

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by learning prior knowledge of seen primitives, \textit{i.e.}, attributes and objects. Learning generalizable compositional r…

Compositional Zero-Shot Learning

Towards the Mitigation of Confirmation Bias in Semi-supervised Learning: a Debiased Training Perspective

2024-09-26 · Yu Wang, Yuxuan Yin, Peng Li

Semi-supervised learning (SSL) commonly exhibits confirmation bias, where models disproportionately favor certain classes, leading to errors in predicted pseudo labels that accumulate under a self-training paradigm. Unli…

image-classificationImage Classification

Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition

2021-11-08 · Jiazhi Li, Wael Abd-Almageed

As equality issues in the use of face recognition have garnered a lot of attention lately, greater efforts have been made to debiased deep learning models to improve fairness to minorities. However, there is still no cle…

Face RecognitionFairness