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 (16)

• In Search of Lost Domain Generalization
• Efficient Domain Generalization via Common-Specific Low-Rank Decomposition
• Domain Adaptive Relational Reasoning for 3D Multi-Organ Segmentation
• Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization
• Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains
• Learning to Learn with Variational Information Bottleneck 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
• Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization
• Domain Generalization via Semi-supervised Meta Learning
• Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment
• Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning
• Learning Image Labels On-the-fly for Training Robust Classification Models
• Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Information
• Style-invariant Cardiac Image Segmentation with Test-time Augmentation
• Discrepancy Minimization in Domain Generalization with Generative Nearest Neighbors