Switchable Whitening for Deep Representation Learning

2019/04/22 by Xingang Pan, Xiaohang Zhan, Pan, Xingang +7 · 20 citations
Computer Science · #Advanced Neural Network Applications #Artificial intelligence #Code (set theory) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convolutional neural network #Deep learning #Domain Adaptation and Few-Shot Learning #Domain adaptation #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine learning #Normalization (sociology) #Pattern recognition (psychology) #Programming language #Representation (politics) #Segmentation #Set (abstract data type) #Standardization #cs.CV

paper · pdf · doi:10.48550/arxiv.1904.09739

published in arXiv (Cornell University) (Cornell University) · Accepted to ICCV2019

openalex publication_date 2019/04/22 · arxiv created 2019/12/12 · arxiv updated 2019/12/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Normalization methods are essential components in convolutional neural networks (CNNs). They either standardize or whiten data using statistics estimated in predefined sets of pixels. Unlike existing works that design normalization techniques for specific tasks, we propose Switchable Whitening (SW), which provides a general form unifying different whitening methods as well as standardization methods. SW learns to switch among these operations in an end-to-end manner. It has several advantages. First, SW adaptively selects appropriate whitening or standardization statistics for different tasks (see Fig.1), making it well suited for a wide range of tasks without manual design. Second, by integrating benefits of different normalizers, SW shows consistent improvements over its counterparts in various challenging benchmarks. Third, SW serves as a useful tool for understanding the characteristics of whitening and standardization techniques. We show that SW outperforms other alternatives on image classification (CIFAR-10/100, ImageNet), semantic segmentation (ADE20K, Cityscapes), domain adaptation (GTA5, Cityscapes), and image style transfer (COCO). For example, without bells and whistles, we achieve state-of-the-art performance with 45.33% mIoU on the ADE20K dataset. Code is available at https://github.com/XingangPan/Switchable-Whitening.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Semantic Understanding of Scenes Through the ADE20K Dataset
• Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Causal-Tune: Mining Causal Factors from Vision Foundation Models for Domain Generalized Semantic Segmentation
• Test-Time Modification: Inverse Domain Transformation for Robust Perception
• Exploiting Domain Properties in Language-Driven Domain Generalization for Semantic Segmentation
• SAGE: Style-Adaptive Generalization for Privacy-Constrained Semantic Segmentation Across Domains
• RobustSurg-Tackling domain generalisation for out-of-distribution surgical scene segmentation
• Domain Generalization for Semantic Segmentation: A Survey
• Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts
• Target-Oriented Single Domain Generalization
• Multi-Granularity Feature Calibration via VFM for Domain Generalized Semantic Segmentation
• Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Models
• Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation
• Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation
• Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios
• Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability
• Towards Conditional Feature Alignment for Cross-Domain Counting
• Single Domain Generalization for Few-Shot Counting via Universal Representation Matching
• On the Importance of Gaussianizing Representations
• Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detection
• DG-DETR: Toward Domain Generalized Detection Transformer
• Boosting Single-domain Generalized Object Detection via Vision-Language Knowledge Interaction
• Image Classification Using CNN-QNN Hybrid Model with Optimized Correlated Features
• Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation

Related

• Switchable Normalization for Learning-to-Normalize Deep Representation
• Differentiable Learning-to-Normalize via Switchable Normalization
• SSN: Learning Sparse Switchable Normalization via SparsestMax
• Improving Generalization of Batch Whitening by Convolutional Unit Optimization
• Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation