Heterogeneous Domain Generalization via Domain Mixup

Abstract

One of the main drawbacks of deep Convolutional Neural Networks (DCNN) is that they lack generalization capability. In this work, we focus on the problem of heterogeneous domain generalization which aims to improve the generalization capability across different tasks, which is, how to learn a DCNN model with multiple domain data such that the trained feature extractor can be generalized to supporting recognition of novel categories in a novel target domain. To solve this problem, we propose a novel heterogeneous domain generalization method by mixing up samples across multiple source domains with two different sampling strategies. Our experimental results based on the Visual Decathlon benchmark demonstrates the effectiveness of our proposed method. The code is released in \url{https://github.com/wyf0912/MIXALL}

References in corpus (7)

• mixup: Beyond Empirical Risk Minimization
• On the Convergence of Adam and Beyond
• Fine-Grained Visual Classification of Aircraft
• Domain Generalization via Invariant Feature Representation
• On First-Order Meta-Learning Algorithms
• Generalizing Across Domains via Cross-Gradient Training
• Feature-Critic Networks for Heterogeneous Domain Generalization

Cited by in corpus (19)

• Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions
• In Search of Lost Domain Generalization
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
• Domain Generalization using Causal Matching
• Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
• Out-of-Distribution Generalization Analysis via Influence Function
• Adaptive Domain Generalization via Online Disagreement Minimization
• Open Domain Generalization with Domain-Augmented Meta-Learning
• Domain Generalization for Session-Independent Brain-Computer Interface
• Model-Based Domain Generalization
• SWAD: Domain Generalization by Seeking Flat Minima
• A Fine-Grained Analysis on Distribution Shift
• Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation
• Cross-domain Transfer of defect features in technical domains based on partial target data
• Explainability-aided Domain Generalization for Image Classification
• Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms
• Learning Generalized Spatial-Temporal Deep Feature Representation for No-Reference Video Quality Assessment
• Towards Data-Free Domain Generalization
• StochCA: A Novel Approach for Exploiting Pretrained Models with Cross-Attention