Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation

Abstract

Training a model to perform a task typically requires a large amount of data from the domains in which the task will be applied. However, it is often the case that data are abundant in some domains but scarce in others. Domain adaptation deals with the challenge of adapting a model trained from a data-rich source domain to perform well in a data-poor target domain. In general, this requires learning plausible mappings between domains. CycleGAN is a powerful framework that efficiently learns to map inputs from one domain to another using adversarial training and a cycle-consistency constraint. However, the conventional approach of enforcing cycle-consistency via reconstruction may be overly restrictive in cases where one or more domains have limited training data. In this paper, we propose an augmented cyclic adversarial learning model that enforces the cycle-consistency constraint via an external task specific model, which encourages the preservation of task-relevant content as opposed to exact reconstruction. We explore digit classification in a low-resource setting in supervised, semi and unsupervised situation, as well as high resource unsupervised. In low-resource supervised setting, the results show that our approach improves absolute performance by 14% and 4% when adapting SVHN to MNIST and vice versa, respectively, which outperforms unsupervised domain adaptation methods that require high-resource unlabeled target domain. Moreover, using only few unsupervised target data, our approach can still outperforms many high-resource unsupervised models. In speech domains, we similarly adopt a speech recognition model from each domain as the task specific model. Our approach improves absolute performance of speech recognition by 2% for female speakers in the TIMIT dataset, where the majority of training samples are from male voices.

arXiv comment14 pages, 5 figures, 8 tables; Accepted as a conference paper at ICLR 2019

References in corpus (10)

• WaveNet: A Generative Model for Raw Audio
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• A DIRT-T Approach to Unsupervised Domain Adaptation
• Unsupervised Cross-Domain Image Generation
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
• Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
• Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation
• Semi-supervised Conditional GANs
• Improving End-to-End Speech Recognition with Policy Learning

Cited by in corpus (13)

• On Learning Invariant Representation for Domain Adaptation
• Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview
• Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation
• TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer
• Semantics-Aware Image to Image Translation and Domain Transfer
• Data Efficient Unsupervised Domain Adaptation for Cross-Modality Image Segmentation
• Relaxed Conditional Image Transfer for Semi-supervised Domain Adaptation
• CUDA: Contradistinguisher for Unsupervised Domain Adaptation
• Unsupervised Domain Adaptation using Generative Models and Self-ensembling
• Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification using Multi-temporal Sentinel-2 Satellite Imagery
• Matching Embeddings for Domain Adaptation
• Unsupervised Domain Adaptation in Speech Recognition using Phonetic Features
• LRS-DAG: Low Resource Supervised Domain Adaptation with Generalization Across Domains