Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation

Abstract

The generalization capability of machine learning models, which refers to generalizing the knowledge for an "unseen" domain via learning from one or multiple seen domain(s), is of great importance to develop and deploy machine learning applications in the real-world conditions. Domain Generalization (DG) techniques aim to enhance such generalization capability of machine learning models, where the learnt feature representation and the classifier are two crucial factors to improve generalization and make decisions. In this paper, we propose Discriminative Adversarial Domain Generalization (DADG) with meta-learning-based cross-domain validation. Our proposed framework contains two main components that work synergistically to build a domain-generalized DNN model: (i) discriminative adversarial learning, which proactively learns a generalized feature representation on multiple "seen" domains, and (ii) meta-learning based cross-domain validation, which simulates train/test domain shift via applying meta-learning techniques in the training process. In the experimental evaluation, a comprehensive comparison has been made among our proposed approach and other existing approaches on three benchmark datasets. The results shown that DADG consistently outperforms a strong baseline DeepAll, and outperforms the other existing DG algorithms in most of the evaluation cases.

References in corpus (11)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition
• Meta-Learning with Implicit Gradients
• Learning Robust Representations by Projecting Superficial Statistics Out
• Learning to Optimize Neural Nets
• Domain-Adversarial Training of Neural Networks
• Feature-Critic Networks for Heterogeneous Domain Generalization
• AutoGAN-based Dimension Reduction for Privacy Preservation
• Enhanced PeerHunter: Detecting Peer-to-peer Botnets through Network-Flow Level Community Behavior Analysis
• SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System
• Utility-aware Privacy-preserving Data Releasing

Cited by in corpus (2)

• Meta-learning and data augmentation for mass-generalised jet taggers
• Discovering Spatial Relationships by Transformers for Domain Generalization