Joint Distribution Of Features Research Articles

Dropout-Based Adversarial Training Networks for Remote Sensing Scene Classification

Scene classification in remote sensing (RS) images is a challenging task due to the lack of well-labeled data. Recently, deep transfer learning (DTL) has been proposed to handle this task. However, the intraclass variations and interclass similarities remain challenges. To handle these challenges, this letter presents a novel dropout-based adversarial training network (DATN) for RS scene classification. Specifically, a dropout-based label classifier (DLC) module is designed to reduce the selection of ambiguous features on class boundaries. Then, a dropout-based domain discriminator (DDD) module is constructed to capture multimodal structures of RS images so as to achieve fine-grained alignment between cross-domain distributions. Third, a joint distribution of features and labels is built to further enhance the performance. Experiments on seven public RS datasets show that our model outperforms several states of the art (SOTAs) under different conditions. The code of our method is publicly available at <uri>https://github.com/WangXin81/DATN-Submitted-to-IEEE-GRSL</uri>.

A novel adversarial transfer learning in deep convolutional neural network for intelligent diagnosis of gas‐insulated switchgear insulation defect

Recently, numerous data-driven fault diagnosis methods have been developed, and the tasks involving the same distribution of training and test data have been well solved. However, considering the particularity of gas-insulated switchgear (GIS), collecting massive data, especially with the same distribution, is difficult. Therefore, existing fault diagnosis methods hardly achieve satisfactory insulation defect diagnosis with small datasets. Aiming at solving this problem, a novel domain adversarial transfer convolutional neural network (DATCNN) is proposed, realising the diagnosis of GIS insulation defects on small samples. First, a residual CNN is built to learn feature representations from the source and target domains. Second, the domain adversarial training strategy is used for feature transfer, where a conditional adversarial mechanism is introduced, and the joint distribution of features and labels is improved to a random linear combination, which realises the simultaneous adaptation of features and labels. Finally, the Nesterov accelerated gradient descent optimisation algorithm is used to speed up the gradient convergence. DATCNN has 99.15% and ≥89.5% diagnosis accuracy for GIS insulation defects in the laboratory and on-site, respectively. Comprehensive experiment results show the effectiveness and superiority of the proposed method in diagnosing GIS insulation defects with small samples.

Margin-Based Adversarial Joint Alignment Domain Adaptation

Domain adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain, which has different data distribution with the source domain. Most of the existing methods focus on aligning the data distribution between the source and target domains but ignore the discrimination of the feature space among categories, leading the samples close to the decision boundary to be misclassified easily. To address the above issue, we propose a Margin-based Adversarial Joint Alignment (MAJA) to constrain the feature spaces of source and target domains to be aligned and discriminative. The proposed MAJA consists of two components: joint alignment module and margin-based generative module. The joint alignment module is proposed to align the source and target feature spaces by considering the joint distribution of features and labels. Therefore, the embedding features and the corresponding labels treated as pair data are applied for domain alignment. Furthermore, the margin-based generative module is proposed to boost the discrimination of the feature space, i.e., make all samples as far away from the decision boundary as possible. The margin-based generative module first employs the Generative Adversarial Networks (GAN) to generate a lot of fake images for each category, then applies the adversarial learning to enlarge and reduce the category margin for the true images and generated fake images, respectively. The evaluations on three benchmarks, e.g., small image datasets, VisDA-2017, and Office-31, verify the effectiveness of the proposed method.

Domain adaptation with feature and label adversarial networks

Learning a cross-domain representation from labeled source domains to unlabeled target domains is an important research problem in representation learning. Despite the success of traditional adversarial methods, they proposed to align features from each domain only while neglecting the importance of labels, when fooling a special domain discriminator network. Thus, the discriminator of these approaches merely distinguishes whether the generated features are in-domain or not, which may lead to less class-discriminative features. In this paper, by considering the joint distributions of features and labels in both domains, we present Feature and Label Adversarial Networks (FLAN). As a result, FLAN can generate more discriminative features in both domains. Experimental results on standard unsupervised domain adaptation benchmarks have demonstrated that FLAN can outperform the state-of-art domain invariant representation learning methods.

Beyond OCR: Multi-faceted understanding of handwritten document characteristics

Handwritten document understanding is a fundamental research problem in pattern recognition and it relies on the effective features. In this paper, we propose a joint feature distribution (JFD) principle to design novel discriminative features which could be the joint distribution of features on adjacent positions or the joint distribution of different features on the same location. Following the proposed JFD principle, we introduce seventeen features, including twelve textural-based and five grapheme-based features. We evaluate these features for different applications from four different perspectives to understand handwritten documents beyond OCR (optical character reognition), by writer identification, script recognition, historical manuscript dating and localization. Extensive experimental results demonstrate that our novel QuadHinge and CoHinge features following the JFD principle provide promising results on these four applications.