Learning Debiased Representations via Conditional Attribute Interpolation
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) is prone to make predictions by the "unintended" attribute, especially if it is easier to learn. To improve the generalization ability when training on such a biased dataset, we propose a chi^2-model to learn debiased representations. First, we design a chi-shape pattern to match the training dynamics of a DNN and find Intermediate Attribute Samples (IASs) --- samples near the attribute decision boundaries, which indicate how the value of an attribute changes from one extreme to another. Then we rectify the representation with a chi-structured metric learning objective. Conditional interpolation among IASs eliminates the negative effect of peripheral attributes and facilitates retaining the intra-class compactness. Experiments show that chi^2-model learns debiased representation effectively and achieves remarkable improvements on various datasets.
Code (1)
Tasks
AttributeMetric LearningSimilar Papers 제목 키워드 기반
Learning by Imagining: Debiased Feature Augmentation for Compositional Zero-Shot Learning
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 LearningUnsupervised Learning of Debiased Representations with Pseudo-Attributes
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 t…
AttributeBalancing Act: Distribution-Guided Debiasing in Diffusion Models
Diffusion Models (DMs) have emerged as powerful generative models with unprecedented image generation capability. These models are widely used for data augmentation and creative applications. However, DMs reflect the bia…
AttributeData AugmentationDenoisingImage GenerationInformation-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition
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 RecognitionFairnessTriple/Debiased Lasso for Statistical Inference of Conditional Average Treatment Effects
This study investigates the estimation and the statistical inference about Conditional Average Treatment Effects (CATEs), which have garnered attention as a metric representing individualized causal effects. In our data-…
regression