Bidirectional Adversarial Training for Semi-Supervised Domain Adaptation

Semi-supervised domain adaptation (SSDA) is a novel branch of machine learning that scarce labeled target examples are available, compared with unsupervised domain adaptation. To make effective use of these additional data so as to bridge the domain gap, one possible way is to generate adversarial examples, which are images with additional perturbations, between the two domains and fill the domain gap. Adversarial training has been proven to be a powerful method for this purpose. However, the traditional adversarial training adds noises in arbitrary directions, which is inefficient to migrate between domains, or generate directional noises from the source to target domain and reverse. In this work, we devise a general bidirectional adversarial training method and employ gradient to guide adversarial examples across the domain gap, i.e., the Adaptive Adversarial Training (AAT) for source to target domain and Entropy-penalized Virtual Adversarial Training (E-VAT) for target to source domain. Particularly, we devise a Bidirectional Adversarial Training (BiAT) network to perform diverse adversarial trainings jointly. We evaluate the effectiveness of BiAT on three benchmark datasets and experimental results demonstrate the proposed method achieves the state-of-the-art.

Download Full-text

Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6262 ◽

2020 ◽

Vol 34 (05) ◽

pp. 7618-7625

Author(s):

Yong Dai ◽

Jian Liu ◽

Xiancong Ren ◽

Zenglin Xu

Keyword(s):

Sentiment Analysis ◽

Domain Adaptation ◽

State Of The Art ◽

Weak Assumption ◽

Target Domain ◽

Smoothness Assumption ◽

Unsupervised Domain Adaptation ◽

Good Target ◽

Adversarial Training ◽

Learning Frameworks

Multi-source unsupervised domain adaptation (MS-UDA) for sentiment analysis (SA) aims to leverage useful information in multiple source domains to help do SA in an unlabeled target domain that has no supervised information. Existing algorithms of MS-UDA either only exploit the shared features, i.e., the domain-invariant information, or based on some weak assumption in NLP, e.g., smoothness assumption. To avoid these problems, we propose two transfer learning frameworks based on the multi-source domain adaptation methodology for SA by combining the source hypotheses to derive a good target hypothesis. The key feature of the first framework is a novel Weighting Scheme based Unsupervised Domain Adaptation framework ((WS-UDA), which combine the source classifiers to acquire pseudo labels for target instances directly. While the second framework is a Two-Stage Training based Unsupervised Domain Adaptation framework (2ST-UDA), which further exploits these pseudo labels to train a target private extractor. Importantly, the weights assigned to each source classifier are based on the relations between target instances and source domains, which measured by a discriminator through the adversarial training. Furthermore, through the same discriminator, we also fulfill the separation of shared features and private features.Experimental results on two SA datasets demonstrate the promising performance of our frameworks, which outperforms unsupervised state-of-the-art competitors.

Download Full-text

Self-Ensembling Attention Networks: Addressing Domain Shift for Semantic Segmentation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33015581 ◽

2019 ◽

Vol 33 ◽

pp. 5581-5588 ◽

Cited By ~ 3

Author(s):

Yonghao Xu ◽

Bo Du ◽

Lefei Zhang ◽

Qian Zhang ◽

Guoli Wang ◽

...

Keyword(s):

Domain Adaptation ◽

State Of The Art ◽

Semantic Segmentation ◽

Great Success ◽

Learning Models ◽

Target Domain ◽

Attention Networks ◽

Source Domain ◽

Benchmark Datasets ◽

Different Levels

Recent years have witnessed the great success of deep learning models in semantic segmentation. Nevertheless, these models may not generalize well to unseen image domains due to the phenomenon of domain shift. Since pixel-level annotations are laborious to collect, developing algorithms which can adapt labeled data from source domain to target domain is of great significance. To this end, we propose self-ensembling attention networks to reduce the domain gap between different datasets. To the best of our knowledge, the proposed method is the first attempt to introduce selfensembling model to domain adaptation for semantic segmentation, which provides a different view on how to learn domain-invariant features. Besides, since different regions in the image usually correspond to different levels of domain gap, we introduce the attention mechanism into the proposed framework to generate attention-aware features, which are further utilized to guide the calculation of consistency loss in the target domain. Experiments on two benchmark datasets demonstrate that the proposed framework can yield competitive performance compared with the state of the art methods.

Download Full-text

Discriminative Adversarial Domain Adaptation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.6054 ◽

2020 ◽

Vol 34 (04) ◽

pp. 5940-5947 ◽

Cited By ~ 2

Author(s):

Hui Tang ◽

Kui Jia

Keyword(s):

Domain Adaptation ◽

Set Domain ◽

Target Domain ◽

Adversarial Learning ◽

Closed Set ◽

Joint Distributions ◽

Open Set ◽

Benchmark Datasets ◽

Adversarial Training ◽

Minimax Game

Given labeled instances on a source domain and unlabeled ones on a target domain, unsupervised domain adaptation aims to learn a task classifier that can well classify target instances. Recent advances rely on domain-adversarial training of deep networks to learn domain-invariant features. However, due to an issue of mode collapse induced by the separate design of task and domain classifiers, these methods are limited in aligning the joint distributions of feature and category across domains. To overcome it, we propose a novel adversarial learning method termed Discriminative Adversarial Domain Adaptation (DADA). Based on an integrated category and domain classifier, DADA has a novel adversarial objective that encourages a mutually inhibitory relation between category and domain predictions for any input instance. We show that under practical conditions, it defines a minimax game that can promote the joint distribution alignment. Except for the traditional closed set domain adaptation, we also extend DADA for extremely challenging problem settings of partial and open set domain adaptation. Experiments show the efficacy of our proposed methods and we achieve the new state of the art for all the three settings on benchmark datasets.

Download Full-text

Bayesian Uncertainty Matching for Unsupervised Domain Adaptation

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/534 ◽

2019 ◽

Cited By ~ 4

Author(s):

Jun Wen ◽

Nenggan Zheng ◽

Junsong Yuan ◽

Zhefeng Gong ◽

Changyou Chen

Keyword(s):

Negative Transfer ◽

Domain Adaptation ◽

Target Domain ◽

Bayesian Neural Network ◽

Prediction Uncertainty ◽

Unsupervised Domain Adaptation ◽

Distribution Matching ◽

Benchmark Datasets ◽

Label Distribution ◽

Target Data

Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by matching marginal feature distributions through deep transformations on the input features, due to the unavailability of target domain labels. We show that domain shift may still exist via label distribution shift at the classifier, thus deteriorating model performances. To alleviate this issue, we propose an approximate joint distribution matching scheme by exploiting prediction uncertainty. Specifically, we use a Bayesian neural network to quantify prediction uncertainty of a classifier. By imposing distribution matching on both features and labels (via uncertainty), label distribution mismatching in source and target data is effectively alleviated, encouraging the classifier to produce consistent predictions across domains. We also propose a few techniques to improve our method by adaptively reweighting domain adaptation loss to achieve nontrivial distribution matching and stable training. Comparisons with state of the art unsupervised domain adaptation methods on three popular benchmark datasets demonstrate the superiority of our approach, especially on the effectiveness of alleviating negative transfer.

Download Full-text

Unsupervised Domain Adaptation on Reading Comprehension

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6245 ◽

2020 ◽

Vol 34 (05) ◽

pp. 7480-7487

Author(s):

Yu Cao ◽

Meng Fang ◽

Baosheng Yu ◽

Joey Tianyi Zhou

Keyword(s):

Reading Comprehension ◽

Large Scale ◽

Domain Adaptation ◽

Generalization Capability ◽

Target Domain ◽

Adversarial Learning ◽

Unsupervised Domain Adaptation ◽

Comparable Performance ◽

Benchmark Datasets ◽

Contextual Representation

Reading comprehension (RC) has been studied in a variety of datasets with the boosted performance brought by deep neural networks. However, the generalization capability of these models across different domains remains unclear. To alleviate the problem, we investigate unsupervised domain adaptation on RC, wherein a model is trained on the labeled source domain and to be applied to the target domain with only unlabeled samples. We first show that even with the powerful BERT contextual representation, a model can not generalize well from one domain to another. To solve this, we provide a novel conditional adversarial self-training method (CASe). Specifically, our approach leverages a BERT model fine-tuned on the source dataset along with the confidence filtering to generate reliable pseudo-labeled samples in the target domain for self-training. On the other hand, it further reduces domain distribution discrepancy through conditional adversarial learning across domains. Extensive experiments show our approach achieves comparable performance to supervised models on multiple large-scale benchmark datasets.

Download Full-text

DC-FUDA: Improving Deep Clustering via Fully Unsupervised Domain Adaptation

10.36227/techrxiv.14995086.v1 ◽

2021 ◽

Author(s):

Zhimeng Yang ◽

Zirui Wu ◽

Ming Zeng ◽

Yazhou Ren ◽

Xiaorong Pu ◽

...

Keyword(s):

Domain Adaptation ◽

State Of The Art ◽

Adaptive Threshold ◽

Generation Process ◽

Target Domain ◽

Source Domain ◽

Unsupervised Domain Adaptation ◽

Adequate Amount ◽

Traditional Approaches ◽

Low Entropy

<div>By transferring knowledge from a source domain, the performance of deep clustering on an unlabeled target domain can be improved. When achieving this, traditional approaches make the assumption that adequate amount of labeled data is available in a source domain. However, this assumption is usually unrealistic in practice. The source domain should be carefully selected to share some characteristics with the target domain, and it can not be guaranteed that rich labeled samples are always available in the selected source domain.</div><div>We propose a novel framework to improve deep clustering by transferring knowledge from a source domain without any labeled data. To select reliable instances in the source domain for transferring, we propose a novel adaptive threshold algorithm to select low entropy instances. To transfer important features of the selected instances, we propose a feature-level domain adaptation network (FeatureDA) which cancels unstable generation process. With extensive experiments, we validate that our method effectively improves deep clustering, without using any labeled data in the source domain. Besides, without using any labeled data in the source domain, our method achieves competitive results, compared to the state-of-the-art methods using labeled data in the source domain.</div>

Download Full-text

Aligning Domain-Specific Distribution and Classifier for Cross-Domain Classification from Multiple Sources

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33015989 ◽

2019 ◽

Vol 33 ◽

pp. 5989-5996 ◽

Cited By ~ 11

Author(s):

Yongchun Zhu ◽

Fuzhen Zhuang ◽

Deqing Wang

Keyword(s):

Domain Adaptation ◽

Feature Space ◽

Multiple Sources ◽

Target Domain ◽

Domain Specific ◽

Unsupervised Domain Adaptation ◽

Specific Distribution ◽

Benchmark Datasets ◽

Invariant Representations ◽

Decision Boundaries

While Unsupervised Domain Adaptation (UDA) algorithms, i.e., there are only labeled data from source domains, have been actively studied in recent years, most algorithms and theoretical results focus on Single-source Unsupervised Domain Adaptation (SUDA). However, in the practical scenario, labeled data can be typically collected from multiple diverse sources, and they might be different not only from the target domain but also from each other. Thus, domain adapters from multiple sources should not be modeled in the same way. Recent deep learning based Multi-source Unsupervised Domain Adaptation (MUDA) algorithms focus on extracting common domain-invariant representations for all domains by aligning distribution of all pairs of source and target domains in a common feature space. However, it is often very hard to extract the same domain-invariant representations for all domains in MUDA. In addition, these methods match distributions without considering domain-specific decision boundaries between classes. To solve these problems, we propose a new framework with two alignment stages for MUDA which not only respectively aligns the distributions of each pair of source and target domains in multiple specific feature spaces, but also aligns the outputs of classifiers by utilizing the domainspecific decision boundaries. Extensive experiments demonstrate that our method can achieve remarkable results on popular benchmark datasets for image classification.

Download Full-text

Bi-Directional Generation for Unsupervised Domain Adaptation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.6137 ◽

2020 ◽

Vol 34 (04) ◽

pp. 6615-6622 ◽

Cited By ~ 2

Author(s):

Guanglei Yang ◽

Haifeng Xia ◽

Mingli Ding ◽

Zhengming Ding

Keyword(s):

Domain Adaptation ◽

State Of The Art ◽

Target Domain ◽

Unsupervised Domain Adaptation ◽

Cross Domain ◽

Proposed Model ◽

Latent Space ◽

Domain Alignment ◽

Domain Information ◽

Adaptation Model

Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. The conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure. To balance the mitigation of domain gap and the preservation of the inherent structure, we propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains. Specifically, two cross-domain generators are employed to synthesize one domain conditioned on the other. The performance of our proposed method can be further enhanced by the consistent classifiers and the cross-domain alignment constraints. We also design two classifiers which are jointly optimized to maximize the consistency on target sample prediction. Extensive experiments verify that our proposed model outperforms the state-of-the-art on standard cross domain visual benchmarks.

Download Full-text

Benchmarking Domain Adaptation Methods on Aerial Datasets

Sensors ◽

10.3390/s21238070 ◽

2021 ◽

Vol 21 (23) ◽

pp. 8070

Author(s):

Navya Nagananda ◽

Abu Md Niamul Taufique ◽

Raaga Madappa ◽

Chowdhury Sadman Jahan ◽

Breton Minnehan ◽

...

Keyword(s):

Deep Learning ◽

Supervised Classification ◽

Domain Adaptation ◽

State Of The Art ◽

Classification Performance ◽

Target Domain ◽

Source Domain ◽

Unsupervised Domain Adaptation ◽

Testing Data ◽

Classification Tasks

Deep learning grew in importance in recent years due to its versatility and excellent performance on supervised classification tasks. A core assumption for such supervised approaches is that the training and testing data are drawn from the same underlying data distribution. This may not always be the case, and in such cases, the performance of the model is degraded. Domain adaptation aims to overcome the domain shift between the source domain used for training and the target domain data used for testing. Unsupervised domain adaptation deals with situations where the network is trained on labeled data from the source domain and unlabeled data from the target domain with the goal of performing well on the target domain data at the time of deployment. In this study, we overview seven state-of-the-art unsupervised domain adaptation models based on deep learning and benchmark their performance on three new domain adaptation datasets created from publicly available aerial datasets. We believe this is the first study on benchmarking domain adaptation methods for aerial data. In addition to reporting classification performance for the different domain adaptation models, we present t-SNE visualizations that illustrate the benefits of the adaptation process.

Download Full-text