Metadata Normalization

Abstract

Batch Normalization (BN) and its variants have delivered tremendous success in combating the covariate shift induced by the training step of deep learning methods. While these techniques normalize feature distributions by standardizing with batch statistics, they do not correct the influence on features from extraneous variables or multiple distributions. Such extra variables, referred to as metadata here, may create bias or confounding effects (e.g., race when classifying gender from face images). We introduce the Metadata Normalization (MDN) layer, a new batch-level operation which can be used end-to-end within the training framework, to correct the influence of metadata on feature distributions. MDN adopts a regression analysis technique traditionally used for preprocessing to remove (regress out) the metadata effects on model features during training. We utilize a metric based on distance correlation to quantify the distribution bias from the metadata and demonstrate that our method successfully removes metadata effects on four diverse settings: one synthetic, one 2D image, one video, and one 3D medical image dataset.

arXiv commentAccepted to CVPR 2021. Project page: https://mml.stanford.edu/MDN/

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Equality of Opportunity in Supervised Learning
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• Learning Adversarially Fair and Transferable Representations
• No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World
• Learning Non-Discriminatory Predictors
• Detect and Correct Bias in Multi-Site Neuroimaging Datasets
• Identifying and Correcting Label Bias in Machine Learning
• Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition
• Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization
• Learning Fair Representations for Kernel Models
• Confounder-Aware Visualization of ConvNets
• AdaBatch: Efficient Gradient Aggregation Rules for Sequential and Parallel Stochastic Gradient Methods