Domain Generalization via Model-Agnostic Learning of Semantic Features

Abstract

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data such that it can directly generalize to target domains with unknown statistics. We adopt a model-agnostic learning paradigm with gradient-based meta-train and meta-test procedures to expose the optimization to domain shift. Further, we introduce two complementary losses which explicitly regularize the semantic structure of the feature space. Globally, we align a derived soft confusion matrix to preserve general knowledge about inter-class relationships. Locally, we promote domain-independent class-specific cohesion and separation of sample features with a metric-learning component. The effectiveness of our method is demonstrated with new state-of-the-art results on two common object recognition benchmarks. Our method also shows consistent improvement on a medical image segmentation task.

NeurIPS 2019

Cited by in corpus (45)

• In Search of Lost Domain Generalization
• Efficient Domain Generalization via Common-Specific Low-Rank Decomposition
• FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space
• Domain Generalization with MixStyle
• Auto-FedAvg: Learnable Federated Averaging for Multi-Institutional Medical Image Segmentation
• FSDR: Frequency Space Domain Randomization for Domain Generalization
• Deep Stable Learning for Out-Of-Distribution Generalization
• Domain Adaptive Relational Reasoning for 3D Multi-Organ Segmentation
• Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization
• Progressive Domain Expansion Network for Single Domain Generalization
• Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains
• Generalizable Person Re-identification with Relevance-aware Mixture of Experts
• Learning to Learn with Variational Information Bottleneck for Domain Generalization
• A Fourier-based Framework for Domain Generalization
• Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation
• Learning Cross-domain Generalizable Features by Representation Disentanglement
• Open Domain Generalization with Domain-Augmented Meta-Learning
• Towards Domain Invariant Single Image Dehazing
• Domain Generalization via Semi-supervised Meta Learning
• Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization
• MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
• Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment
• Domain Generalization for Session-Independent Brain-Computer Interface
• AtrialGeneral: Domain Generalization for Left Atrial Segmentation of Multi-Center LGE MRIs
• Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment
• Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization
• Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning
• Uncertainty-guided Model Generalization to Unseen Domains
• Self-balanced Learning For Domain Generalization
• Learning Image Labels On-the-fly for Training Robust Classification Models
• Multi-task Learning by Leveraging the Semantic Information
• Style-invariant Cardiac Image Segmentation with Test-time Augmentation
• Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Information
• Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation
• Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation
• Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation
• Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms
• Explainability-aided Domain Generalization for Image Classification
• Discrepancy Minimization in Domain Generalization with Generative Nearest Neighbors
• Histogram Matching Augmentation for Domain Adaptation with Application to Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Image Segmentation
• Discovering Spatial Relationships by Transformers for Domain Generalization
• An Empirical Framework for Domain Generalization in Clinical Settings
• Robust Domain-Free Domain Generalization with Class-aware Alignment
• Mutual Information-based Disentangled Neural Networks for Classifying Unseen Categories in Different Domains: Application to Fetal Ultrasound Imaging
• Domain Composition and Attention for Unseen-Domain Generalizable Medical Image Segmentation