Network Architecture Search for Domain Adaptation
arXiv:2008.05706
Abstract
Deep networks have been used to learn transferable representations for domain adaptation. Existing deep domain adaptation methods systematically employ popular hand-crafted networks designed specifically for image-classification tasks, leading to sub-optimal domain adaptation performance. In this paper, we present Neural Architecture Search for Domain Adaptation (NASDA), a principle framework that leverages differentiable neural architecture search to derive the optimal network architecture for domain adaptation task. NASDA is designed with two novel training strategies: neural architecture search with multi-kernel Maximum Mean Discrepancy to derive the optimal architecture, and adversarial training between a feature generator and a batch of classifiers to consolidate the feature generator. We demonstrate experimentally that NASDA leads to state-of-the-art performance on several domain adaptation benchmarks.
References in corpus (19)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Learning Transferable Features with Deep Adaptation Networks
- Deep Domain Confusion: Maximizing for Domain Invariance
- Conditional Adversarial Domain Adaptation
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
- Domain Separation Networks
- A DIRT-T Approach to Unsupervised Domain Adaptation
- A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
- Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
- Efficient Architecture Search by Network Transformation
- SNAS: Stochastic Neural Architecture Search
- Hyperparameter optimization with approximate gradient
- Freeze-Thaw Bayesian Optimization
- Co-regularized Alignment for Unsupervised Domain Adaptation
- Bilevel Programming for Hyperparameter Optimization and Meta-Learning
- Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters
- Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search
- Self-ensembling for visual domain adaptation
- Learning Smooth Representation for Unsupervised Domain Adaptation