A Unified Adversarial Learning Framework for Semi-supervised Multi-target Domain Adaptation

Since labeled data availability differs greatly across domains, Domain Adaptation focuses on learning in new and unfamiliar domains by reducing distribution divergence. Recent research suggests that the adversarial learning approach could be a promising way to achieve the domain adaptation objective. Adversarial learning is a strategy for learning domain-transferable features in robust deep networks. This paper introduces the TSAL paradigm, a two-step adversarial learning framework. It addresses the real-world problem of text classification, where source domain(s) has labeled data but target domain (s) has only unlabeled data. TSAL utilizes joint adversarial learning with class information and domain alignment deep network architecture to learn both domain-invariant and domain-specific features extractors. It consists of two training steps that are similar to the paradigm, in which pre-trained model weights are used as initialization for training with new data. TSAL’s two training phases, however, are based on the same data, not different data, as is the case with fine-tuning. Furthermore, TSAL only uses the learned domain-invariant feature extractor from the first training as an initialization for its peer in subsequent training. By doubling the training, TSAL can emphasize the leverage of the small unlabeled target domain and learn effectively what to share between various domains. A detailed analysis of many benchmark datasets reveals that our model consistently outperforms the prior art across a wide range of dataset distributions.

Download Full-text

Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto Ranking

Remote Sensing ◽

10.3390/rs12111716 ◽

2020 ◽

Vol 12 (11) ◽

pp. 1716

Author(s):

Reham Adayel ◽

Yakoub Bazi ◽

Haikel Alhichri ◽

Naif Alajlan

Keyword(s):

High Resolution ◽

Domain Adaptation ◽

Target Domain ◽

Adversarial Learning ◽

Pareto Ranking ◽

Cross Domain ◽

Open Set ◽

Ranking Scheme ◽

High Resolution Images ◽

Alignment Process

Most of the existing domain adaptation (DA) methods proposed in the context of remote sensing imagery assume the presence of the same land-cover classes in the source and target domains. Yet, this assumption is not always realistic in practice as the target domain may contain additional classes unknown to the source leading to the so-called open set DA. Under this challenging setting, the problem turns to reducing the distribution discrepancy between the shared classes in both domains besides the detection of the unknown class samples in the target domain. To deal with the openset problem, we propose an approach based on adversarial learning and pareto-based ranking. In particular, the method leverages the distribution discrepancy between the source and target domains using min-max entropy optimization. During the alignment process, it identifies candidate samples of the unknown class from the target domain through a pareto-based ranking scheme that uses ambiguity criteria based on entropy and the distance to source class prototype. Promising results using two cross-domain datasets that consist of very high resolution and extremely high resolution images, show the effectiveness of the proposed method.

Download Full-text

Fuzzy Graph Learning Regularized Sparse Filtering for Visual Domain Adaptation

Applied Sciences ◽

10.3390/app11104503 ◽

2021 ◽

Vol 11 (10) ◽

pp. 4503

Author(s):

Lingtong Min ◽

Deyun Zhou ◽

Xiaoyang Li ◽

Qinyi Lv ◽

Yuanjie Zhi

Keyword(s):

Domain Adaptation ◽

Weather Conditions ◽

Optimization Method ◽

Superior Performance ◽

Target Domain ◽

Graph Learning ◽

Learning Framework ◽

Cross Domain ◽

Sparse Filtering ◽

Visual Domain

Distribution mismatch can be easily found in multi-sensor systems, which may be caused by different shoot angles, weather conditions and so on. Domain adaptation aims to build robust classifiers using the knowledge from a well-labeled source domain, while applied on a related but different target domain. Pseudo labeling is a prevalent technique for class-wise distribution alignment. Therefore, numerous efforts have been spent on alleviating the issue of mislabeling. In this paper, unlike existing selective hard labeling works, we propose a fuzzy labeling based graph learning framework for matching conditional distribution. Specifically, we construct the cross-domain affinity graph by considering the fuzzy label matrix of target samples. In order to solve the problem of representation shrinkage, the paradigm of sparse filtering is introduced. Finally, a unified optimization method based on gradient descent is proposed. Extensive experiments show that our method achieves comparable or superior performance when compared to state-of-the-art works.

Download Full-text

OVL: One-View Learning for Human Retrieval

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6804 ◽

2020 ◽

Vol 34 (07) ◽

pp. 11410-11417

Author(s):

Wenjing Li ◽

Zhongcheng Wu

Keyword(s):

Large Scale ◽

Domain Adaptation ◽

State Of The Art ◽

Set Domain ◽

Adversarial Learning ◽

Learning Framework ◽

Training Images ◽

Open Set ◽

Camera View ◽

Supervised Methods

This paper considers a novel problem, named One-View Learning (OVL), in human retrieval a.k.a. person re-identification (re-ID). Unlike fully-supervised learning, OVL only requires pretty cheap annotation cost: labeled training images are only provided from one camera view (source view/domain), while the annotations of training images from other camera views (target views/domains) are not available. OVL is a problem of multi-target open set domain adaptation that is difficult for existing domain adaptation methods to handle. This is because 1) unlabeled samples are drawn from multiple target views in different distributions, and 2) the target views may contain samples of “unknown identity” that are not shared by the source view. To address this problem, this work introduces a novel one-view learning framework for person re-ID. This is achieved by adversarial multi-view learning (AMVL) and adversarial unknown rejection learning (AURL). The former learns a multi-view discriminator by adversarial learning to align the feature distributions between all views. The later is designed to reject unknown samples from target views through adversarial learning with two unknown identity classifiers. Extensive experiments on three large-scale datasets demonstrate the advantage of the proposed method over state-of-the-art domain adaptation and semi-supervised methods.

Download Full-text

Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.5943 ◽

2020 ◽

Vol 34 (04) ◽

pp. 5029-5036

Author(s):

You-Wei Luo ◽

Chuan-Xian Ren ◽

Pengfei Ge ◽

Ke-Kun Huang ◽

Yu-Feng Yu

Keyword(s):

Deep Learning ◽

Manifold Learning ◽

Domain Adaptation ◽

Global Approximation ◽

Target Domain ◽

Learning Framework ◽

Unsupervised Domain Adaptation ◽

Manifold Embedding ◽

Rich Information ◽

The Rich

Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. Though deep learning and adversarial strategy make an important breakthrough in the adaptability of features, there are two issues to be further explored. First, the hard-assigned pseudo labels on the target domain are risky to the intrinsic data structure. Second, the batch-wise training manner in deep learning limits the description of the global structure. In this paper, a Riemannian manifold learning framework is proposed to achieve transferability and discriminability consistently. As to the first problem, this method establishes a probabilistic discriminant criterion on the target domain via soft labels. Further, this criterion is extended to a global approximation scheme for the second issue; such approximation is also memory-saving. The manifold metric alignment is exploited to be compatible with the embedding space. A theoretical error bound is derived to facilitate the alignment. Extensive experiments have been conducted to investigate the proposal and results of the comparison study manifest the superiority of consistent manifold learning framework.

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

Comparison of domain adaptation techniques for white matter hyperintensity segmentation in brain MR images

10.1101/2021.03.12.435171 ◽

2021 ◽

Author(s):

Vaanathi Sundaresan ◽

Giovanna Zamboni ◽

Nicola K. Dinsdale ◽

Peter M. Rothwell ◽

Ludovica Griffanti ◽

...

Keyword(s):

White Matter ◽

Transfer Learning ◽

Domain Adaptation ◽

White Matter Hyperintensity ◽

Mr Images ◽

Target Domain ◽

Baseline Model ◽

Adversarial Learning ◽

Adversarial Training ◽

Brain Mr Images

AbstractRobust automated segmentation of white matter hyperintensities (WMHs) in different datasets (domains) is highly challenging due to differences in acquisition (scanner, sequence), population (WMH amount and location) and limited availability of manual segmentations to train supervised algorithms. In this work we explore various domain adaptation techniques such as transfer learning and domain adversarial learning methods, including domain adversarial neural networks and domain unlearning, to improve the generalisability of our recently proposed triplanar ensemble network, which is our baseline model. We evaluated the domain adaptation techniques on source and target domains consisting of 5 different datasets with variations in intensity profile, lesion characteristics and acquired using different scanners. For transfer learning, we also studied various training options such as minimal number of unfrozen layers and subjects required for finetuning in the target domain. On comparing the performance of different techniques on the target dataset, unsupervised domain adversarial training of neural network gave the best performance, making the technique promising for robust WMH segmentation.

Download Full-text

Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss

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

10.24963/ijcai.2018/96 ◽

2018 ◽

Cited By ~ 45

Author(s):

Qi Dou ◽

Cheng Ouyang ◽

Cheng Chen ◽

Hao Chen ◽

Pheng-Ann Heng

Keyword(s):

Domain Adaptation ◽

Feature Space ◽

Learning Approaches ◽

Target Domain ◽

Convolutional Network ◽

Adversarial Learning ◽

Biomedical Image ◽

Convolutional Networks ◽

Ct Data ◽

Set Up

Convolutional networks (ConvNets) have achieved great successes in various challenging vision tasks. However, the performance of ConvNets would degrade when encountering the domain shift. The domain adaptation is more significant while challenging in the field of biomedical image analysis, where cross-modality data have largely different distributions. Given that annotating the medical data is especially expensive, the supervised transfer learning approaches are not quite optimal. In this paper, we propose an unsupervised domain adaptation framework with adversarial learning for cross-modality biomedical image segmentations. Specifically, our model is based on a dilated fully convolutional network for pixel-wise prediction. Moreover, we build a plug-and-play domain adaptation module (DAM) to map the target input to features which are aligned with source domain feature space. A domain critic module (DCM) is set up for discriminating the feature space of both domains. We optimize the DAM and DCM via an adversarial loss without using any target domain label. Our proposed method is validated by adapting a ConvNet trained with MRI images to unpaired CT data for cardiac structures segmentations, and achieved very promising results.

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

Consensus Adversarial Domain Adaptation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33015997 ◽

2019 ◽

Vol 33 ◽

pp. 5997-6004 ◽

Cited By ~ 12

Author(s):

Han Zou ◽

Yuxun Zhou ◽

Jianfei Yang ◽

Huihan Liu ◽

Hari Prasanna Das ◽

...

Keyword(s):

Domain Adaptation ◽

Spatial Dynamics ◽

Feature Space ◽

Target Domain ◽

Adversarial Learning ◽

Digit Recognition ◽

Real World Problem ◽

Benchmark Datasets ◽

Free Gesture ◽

Device Free

We propose a novel domain adaptation framework, namely Consensus Adversarial Domain Adaptation (CADA), that gives freedom to both target encoder and source encoder to embed data from both domains into a common domaininvariant feature space until they achieve consensus during adversarial learning. In this manner, the domain discrepancy can be further minimized in the embedded space, yielding more generalizable representations. The framework is also extended to establish a new few-shot domain adaptation scheme (F-CADA), that remarkably enhances the ADA performance by efficiently propagating a few labeled data once available in the target domain. Extensive experiments are conducted on the task of digit recognition across multiple benchmark datasets and a real-world problem involving WiFi-enabled device-free gesture recognition under spatial dynamics. The results show the compelling performance of CADA versus the state-of-the-art unsupervised domain adaptation (UDA) and supervised domain adaptation (SDA) methods. Numerical experiments also demonstrate that F-CADA can significantly improve the adaptation performance even with sparsely labeled data in the target domain.

Download Full-text