Adversarial Domain Adaptation Method Research Articles

A three-stage bearing transfer fault diagnosis method for large domain shift scenarios

In recent years, significant progress has been achieved in the intelligent fault diagnosis of bearings based on transfer learning. However, existing methods overlook the presence of domain-specific features that are non-transferable when aligning domain distributions. Additionally, the reliability of subdomain alignment has not been adequately evaluated. This severely restricts the diagnostic performance of transfer learning, especially in scenarios of large domain shifts. To address these issues, this paper proposes a novel approach based on three-stage transfer alignment. In the first stage, two private encoders, and a shared encoder are designed to eliminate domain-specific features, thus maximizing the effectiveness and transferability of shared encoded features. Subsequently, in the second stage, a deep adversarial domain adaptation method is introduced to adapt the global distributions between the two domains. Lastly, the third stage presents a novel soft pseudo-label distillation method, based on adaptive entropy weighting. This enhances alignment between subdomains, further bridging the distribution gap between the two domains. A series of comprehensive experiments under two types of large domain shift scenarios validate that the proposed method has a superior performance and could boost 6.93% and 6.14% accuracy than the state-of-the-art methods, respectively.

Specific emitter identification unaffected by time through adversarial domain adaptation and continual learning

Timely identifying the emitter of target signals is crucial for communication security in complex electromagnetic environments. Specific emitter identification (SEI) is a technique to identify emitters using the hardware fingerprints of emitters. In this paper, the impact of changes in hardware fingerprints over time on SEI is solved, which significantly deteriorates identification performance. This issue is addressed from two aspects: one is mitigating the impact of these changes, and the other is tracking and adapting to them. For the aspect of mitigating impact, an alternating adversarial domain adaptation (AADA) method is proposed to eliminate the time-varying component in hardware fingerprints. Subsequently, a feature map calculation method using weighted Euclidean distance is designed, preserving the main parameters of feature maps for each emitter. For the aspect of tracking and adapting to changes, a continual learning method was designed based on feature maps of each emitter. This approach incorporates the selective annotation of unlabeled new data with an iterative optimization training process. To validate the effectiveness of the proposed method, we independently collected comprehensive time-variant datasets as well as simpler datasets with varying receivers and environments. The proposed method was tested on these datasets and compared with existing conventional and advanced methods. The experimental results indicate that the proposed SEI method exhibits superior recognition performance. Compared to existing methods, it achieved an average recognition accuracy improvement of over 8% on the time-variant dataset, and demonstrated enhanced robustness against these three types of variations.

Research on maintenance cycle prediction for energy equipment with limited and sensitive data

Failures in natural gas compressor units can lead to significant production incidents that impact energy security, making intelligent preventative maintenance of this equipment critically important. Given the limited and sensitive data from critical energy equipment like natural gas compressor units, this paper conducts preventative maintenance research based on domain adaptation and federated learning (DFPM), and proposes a novel maintenance cycle prediction framework. The feasibility of the proposed method was validated through historical operational data from field natural gas compressor units, providing a data-oriented reference for maintenance decision-making. Verification results demonstrate that the proposed multi-level adversarial domain adaptation method possesses superior feature representation capability, enhancing the preservation of the original degradation trend for time series data compared to traditional DA models. The novel federated adversarial strategy presented in this paper can effectively transfer source domain knowledge to the target domain, further enhancing the cross-unit predictive performance of the target domain model with limited samples. Additionally, this strategy with the chaotic multi-mode predictive model further improves the limitations of low parallelism and efficiency in traditional RNN-based prediction models while ensuring data security. This research provides a new perspective for the intelligent operation and maintenance of large energy equipment, which is of significance in practical engineering.

Similar norm more transferable: Rethinking feature norms discrepancy in adversarial domain adaptation

Adversarial learning has become an effective paradigm for learning transferable features in domain adaptation. However, many previous adversarial domain adaptation methods inevitably damage the discriminative information contained in transferable features, which limits the potential of adversarial learning. In this paper, we explore the reason for this phenomenon and find that the model pays more attention to the alignment of feature norms than the learning of domain-invariant features during adversarial adaptation. Moreover, we observe that the feature norms contain some crucial category information, which is ignored in previous studies. To achieve better adversarial adaptation, we propose two novel feature norms alignment strategies: Histogram-guided Norms Alignment (HNA) and Transport-guided Norms Alignment (TNA). Both strategies model the feature norms from the distribution perspective, which not only facilitates the reduction of the norms discrepancy but also makes full use of discriminative information contained in the norms. Extensive experiments demonstrate that progressively aligning the feature norms distributions of two domains can effectively promote the capture of semantically rich shared features and significantly boost the model’s transfer performance. We hope our findings can shed some light on future research of adversarial domain adaptation.

Unsupervised Logo Detection Using Adversarial Learning From Synthetic to Real Images

Most existing deep learning-based methods for logo detection require a large amount of object-level annotated training data. However, it takes a lot of time and effort to create a good object-level annotated logo detection dataset. Many researchers have tried to utilize synthesized images with automatically generated annotations for training to deal with data annotation problem. However, in real applications, model trained using synthesized images suffer from performance loss due to domain shift between synthesized and real-world images. To this end, in this paper, we propose an adversarial learning-based unsupervised domain adaptation method for logo detection. We only use labeled synthesized logo images for model training and adapt target domain knowledge using unlabeled real-world logo images. We propose entropy minimization of mid-level output feature maps in order to effectively align the domain gap between synthetic and real images for the logo detection task. Additionally, we have generated coherent synthesized logo images with automatically constructed bounding box annotations for different datasets to perform unsupervised training for the experiments. Our experiments show that the proposed method improves performance on different logo datasets compared to direct transfer from source to target domain (synthetic-to-real images) without any labeling cost and increasing network parameters.

Multi-source partial domain adaptation method based on pseudo-balanced target domain for fault diagnosis

Multisource domain adaptation (MSDA) for fault diagnosis enables knowledge transfer from multisource domains to unknown target domains, which is crucial for enhancing equipment reliability and safety. However, current MSDA methods face two major challenges: (1) they face serious domain-shift problems not only between the target and source domains, but also between different source domains, and (2) in practical applications, class labels in the target domain are likely to be subsets of class labels in the source domain. Therefore, this study considers a setting called multisource partial domain adaptation (MSPDA). A two-stage intelligent fault diagnosis method for MSPDA based on pseudo-balanced target domains (PBTD) is proposed. In the first stage, we propose a weighted adversarial partial domain adaptation method based on a dual progressive strategy that aligns each source domain with the target domain to construct a series of PBTD. In the second stage, an alternating learning scheme is utilized to align the remaining source domains with the PBTDs, which makes full use of multisource information to bridge the discrepancies between different domains. Additionally, this study proposes a multiscale convolutional neural network based on a three-branch attention mechanism that captures the cross-dimensional interactions of scale, channel, and space to enhance the algorithmic characterization capability. Finally, extensive experiments with gear and bearing datasets are conducted to validate the effectiveness of the proposed method.

Trust-aware conditional adversarial domain adaptation with feature norm alignment

Adversarial learning has proven to be an effective method for capturing transferable features for unsupervised domain adaptation. However, some existing conditional adversarial domain adaptation methods assign equal importance to different samples, ignoring the fact that hard-to-transfer samples might damage the conditional adversarial adaptation procedure. Meanwhile, some methods can only roughly align marginal distributions across domains, but cannot ensure category distributions alignment, causing classifiers to make uncertain or even wrong predictions for some target data. Furthermore, we find that the feature norms of real images usually follow a complex distribution, so directly matching the mean feature norms of two domains cannot effectively reduce the statistical discrepancy of feature norms and may potentially induce feature degradation.In this paper, we develop a Trust-aware Conditional Adversarial Domain Adaptation (TCADA) method for solving the aforementioned issues. To quantify data transferability, we suggest utilizing posterior probability modeled by a Gaussian-uniform mixture, which effectively facilitates conditional domain alignment. Based on this posterior probability, a confidence-guided alignment strategy is presented to promote precise alignment of category distributions and accelerate the learning of shared features. Moreover, a novel optimal transport-based strategy is introduced to align the feature norms and facilitate shared features becoming more informative. To encourage classifiers to make more accurate predictions for target data, we also design a mixed information-guided entropy regularization term to promote deep features being away from the decision boundaries. Extensive experiments show that our method greatly improves transfer performance on various tasks.

Domain randomization using synthetic electrocardiograms for training neural networks

We present a method for training neural networks with synthetic electrocardiograms that mimic signals produced by a wearable single lead electrocardiogram monitor. We use domain randomization where the synthetic signal properties such as the waveform shape, RR-intervals and noise are varied for every training example. Models trained with synthetic data are compared to their counterparts trained with real data. Detection of r-waves in electrocardiograms recorded during different physical activities and in atrial fibrillation is used to assess the performance. By allowing the randomization of the synthetic signals to increase beyond what is typically observed in the real-world data the performance is on par or superseding the performance of networks trained with real data. Experiments show robust model performance using different seeds and on different unseen test sets that were fully separated from the training phase. The ability of the model to generalize well to hidden test sets without any specific tuning provides a simple and explainable alternative to more complex adversarial domain adaptation methods for model generalization. This method opens up the possibility of extending the use of synthetic data towards domain insensitive cardiac disease classification when disease specific a priori information is used in the electrocardiogram generation. Additionally, the method provides training with free-to-collect data with accurate labels, control of the data distribution eliminating class imbalances that are typically observed in health-related data, and the generated data is inherently private.

Transferable visual pattern memory network for domain adaptation in anomaly detection

Anomaly detection transfer aims to utilize knowledge learned from source anomaly detection task to improve the performance of target anomaly detection task. Conventional methods typically assume that labeled normal or abnormal data are available in the source or target domain. However, many real-world applications do not satisfy this assumption because such labels are hard to collect. This study focuses on the case where anomalous labels are unavailable. More specifically, a rarely studied scenario in which the target domain contains unlabeled normal and abnormal instances, whereas only normal instances are available in the source domain, is addressed. To this end, a transferable visual pattern memory network was designed to transfer knowledge for anomaly detection tasks. The network comprises an adversarial domain adaptation method to extract transferable visual patterns, and a memory module utilized to store these patterns. The model utilizes transferable patterns stored in memory to identify anomalous samples. Moreover, a self-supervised objective is integrated to enhance the discriminability of target abnormal instances, thereby improving the anomaly detection performance. The results of extensive experiments conducted on publicly available anomaly-detection datasets verified the efficacy of the proposed approach.

Mutual Information-Driven Subject-Invariant and Class-Relevant Deep Representation Learning in BCI.

In recent years, deep learning-based feature representation methods have shown a promising impact on electroencephalography (EEG)-based brain-computer interface (BCI). Nonetheless, owing to high intra- and inter-subject variabilities, many studies on decoding EEG were designed in a subject-specific manner by using calibration samples, with no concern of its practical use, hampered by time-consuming steps and a large data requirement. To this end, recent studies adopted a transfer learning strategy, especially domain adaptation techniques. Among those, we have witnessed the potential of adversarial learning-based transfer learning in BCIs. In the meantime, it is known that adversarial learning-based domain adaptation methods are prone to negative transfer that disrupts learning generalized feature representations, applicable to diverse domains, for example, subjects or sessions in BCIs. In this article, we propose a novel framework that learns class-relevant and subject-invariant feature representations in an information-theoretic manner, without using adversarial learning. To be specific, we devise two operational components in a deep network that explicitly estimate mutual information between feature representations: 1) to decompose features in an intermediate layer into class-relevant and class-irrelevant ones and 2) to enrich class-discriminative feature representation. On two large EEG datasets, we validated the effectiveness of our proposed framework by comparing with several comparative methods in performance. Furthermore, we conducted rigorous analyses by performing an ablation study in regard to the components in our network, explaining our model's decision on input EEG signals via layer-wise relevance propagation, and visualizing the distribution of learned features via t-SNE.

Adversarial Mixup Ratio Confusion for Unsupervised Domain Adaptation

Multimedia applications often involve knowledge transfer across domains, e.g., from images to texts, where Unsupervised Domain Adaptation (UDA) can be used to reduce the domain shifts. Most of the UDA methods are based on adversarial learning. However, previous adversarial domain adaptation methods may suffer from three issues. First, although the features learned by previous methods could fool the domain classifier to make false classification predictions, they may not be domain-invariant. Second, the limited number of training samples make the latent space of features not smooth and continuous enough. Third, the target domain features may lack discriminability. In this paper, we propose a novel adversarial domain adaptation method named Adversarial Mixup Ratio Confusion (AMRC) to alleviate all the above issues. Specifically, we propose a new adversarial training pattern that uses mixup to generate multiple features with different mixup ratios, which represent different intermediate states between the source and target domain. Then, on one hand, we train an estimator to estimate the mixup ratio as accurately as possible. On the other hand, we train a generator to make the estimator be uncertain about the mixup ratio. In this way, our method could learn a continuous and domain-invariant latent space. Furthermore, we apply the intra-domain and cross-domain mixup regularizations to ensure the smoothness and continuity of the latent space, while making the classifier behave more linearly on in-between samples. At last, we exploit the sharpened pseudo-labels of the target samples for self-supervised learning to enhance the discriminability of the target features. The experimental results on 3 benchmarks verify the effectiveness of our method.

Unsupervised Domain Adaptation for Remote Sensing Image Segmentation Based on Adversarial Learning and Self-Training

There is a large amount of out-of-distribution data (OOD) in remote sensing, which hinders high-accuracy segmentation models under the assumption of independent identical distribution (i.i.d.) from stable and reliable performance in real-world remote sensing applications. And Domain Adaptation (DA) is presented to seamlessly extend classifiers to the label-scarce target domain in the presence of the label-sufficient source domain with different data distributions. However, given that the domain shift, i.e. the distribution difference between the two domains, is more serious in remote sensing images, the current DA methods for image segmentation in Computer Vision (CV) typically perform unsatisfactorily in remote sensing, even suffering from the negative domain alignment. To this end, this paper proposes the Self-Training Adversarial Domain Adaptation (STADA) method for remote sensing image segmentation, which not only performs adversarial learning to extract domain-invariant features, but also implements Self-Training using pseudo-labels in the target domain denoised by the conditional adversarial loss for classifier adaptation. The ISPRS and WHU datasets are employed to conduct extensive experiments to investigate the effectiveness of STADA and the specific effect of its each DA component. And the experimental results demonstrate that STADA outperforms other state-of-the-art DA methods in the remote sensing image segmentation task.

Unsupervised Adversarial Domain Adaptation for Sim-to-Real Transfer of Tactile Images

Transferring optical tactile skills learned from simulated environments to the real world benefits many robotic tactile applications, which can reduce the cost of data collection. However, the models purely trained on simulated data are often difficult to generalize well to the unseen real world due to the domain gap between the faultless training images and testing images with unpredictable manufacturing defects or natural wear. In this paper, we propose an Adaptively Correlation-attentive and Task-related Network (ACTNet) for tactile image transfer, a novel unsupervised adversarial domain adaptation method to narrow the domain gap for pixel-level tactile perception tasks. An adaptively correlative attention mechanism is introduced to improve the generator, which is capable of leveraging global information and focusing on salient regions. We also construct a task-related constraint loss based on the tactile image classification task to facilitate the zero-shot sim-to-real transfer of the tactile image classifier. Extensive experiment results on tactile image generation and tactile image classification indicate that our method outperforms the state-of-the-art method. Classification accuracy of 92.85% in the real-world environment is achieved without using any real-world classification labels.

A generative adversarial network-based unsupervised domain adaptation method for magnetic resonance image segmentation

Intelligent medical image segmentation methods have been rapidly developed and applied, while a significant challenge is domain shift. That is, the segmentation performance degrades due to distribution differences between the source domain and the target domain. This paper proposed an unsupervised end-to-end domain adaptation medical image segmentation method based on the generative adversarial network (GAN). A network training and adjustment model was designed, including segmentation and discriminant networks. In the segmentation network, the residual module was used as the basic module to increase feature reusability and reduce model optimization difficulty. Further, it learned cross-domain features at the image feature level with the help of the discriminant network and a combination of segmentation loss with adversarial loss. The discriminant network took the convolutional neural network and used the labels from the source domain, to distinguish whether the segmentation result of the generated network is from the source domain or the target domain. The whole training process was unsupervised. The proposed method was tested with experiments on a public dataset of knee magnetic resonance (MR) images and the clinical dataset from our cooperative hospital. With our method, the mean Dice similarity coefficient (DSC) of segmentation results increased by 2.52% and 6.10% to the classical feature level and image level domain adaptive method. The proposed method effectively improves the domain adaptive ability of the segmentation method, significantly improves the segmentation accuracy of the tibia and femur, and can better solve the domain transfer problem in MR image segmentation.

Unsupervised Adversarial Domain Adaptation for Agricultural Land Extraction of Remote Sensing Images

Agricultural land extraction is an essential technical means to promote sustainable agricultural development and modernization research. Existing supervised algorithms rely on many finely annotated remote-sensing images, which is both time-consuming and expensive. One way to reduce the annotation cost approach is to migrate models trained on existing annotated data (source domain) to unannotated data (target domain). However, model generalization capability is often unsatisfactory due to the limit of the domain gap. In this work, we use an unsupervised adversarial domain adaptation method to train a neural network to close the gap between the source and target domains for unsupervised agricultural land extraction. The overall approach consists of two phases: inter-domain and intra-domain adaptation. In the inter-domain adaptation, we use a generative adversarial network (GAN) to reduce the inter-domain gap between the source domain (labeled dataset) and the target domain (unlabeled dataset). The transformer with robust long-range dependency modeling acts as the backbone of the generator. In addition, the multi-scale feature fusion (MSFF) module is designed in the generator to accommodate remote sensing datasets with different spatial resolutions. Further, we use an entropy-based approach to divide the target domain. The target domain is divided into two subdomains, easy split images and hard split images. By training against each other between the two subdomains, we reduce the intra-domain gap. Experiments results on the “DeepGlobe → LoveDA”, “GID → LoveDA” and “DeepGlobe → GID” unsupervised agricultural land extraction tasks demonstrate the effectiveness of our method and its superiority to other unsupervised domain adaptation techniques.

Semi-supervised adversarial discriminative domain adaptation.

Domain adaptation is a potential method to train a powerful deep neural network across various datasets. More precisely, domain adaptation methods train the model on training data and test that model on a completely separate dataset. The adversarial-based adaptation method became popular among other domain adaptation methods. Relying on the idea of GAN, the adversarial-based domain adaptation tries to minimize the distribution between the training and testing dataset based on the adversarial learning process. We observe that the semi-supervised learning approach can combine with the adversarial-based method to solve the domain adaptation problem. In this paper, we propose an improved adversarial domain adaptation method called Semi-Supervised Adversarial Discriminative Domain Adaptation (SADDA), which can outperform other prior domain adaptation methods. We also show that SADDA has a wide range of applications and illustrate the promise of our method for image classification and sentiment classification problems.

A Novel Joint Adversarial Domain Adaptation Method for Rotary Machine Fault Diagnosis under Different Working Conditions.

In real-world applications of detecting faults, many factors-such as changes in working conditions, equipment wear, and environmental causes-can cause a significant mismatch between the source domain on which classifiers are trained and the target domain to which those classifiers are applied. As such, existing deep network algorithms perform poorly under different working conditions. To solve this problem, we propose a novel fault diagnosis method named Joint Adversarial Domain Adaptation (JADA) for fault detection under different working conditions. Our approach simultaneously aligns marginal distribution and conditional distribution across the source and target through a unified adversarial learning process. JADA aims to construct domain-invariant and category-discriminative feature representation that is effective and robust for substantial distribution difference caused by working conditions. We also introduce a supervision signal, namely center loss, that penalizes the distances between the deep features and their corresponding class centers. This makes the learned features better equipped with more discriminative structures and effectively prevents mode collapse. Twenty-four transfer fault diagnosis tasks based on two experimental platforms were conducted to evaluate the effectiveness of the proposed methods. Extensive experiments verified that the JADA can significantly outperform several popular methods under different transfer diagnosis tasks.

Adversarial Entropy Optimization for Unsupervised Domain Adaptation.

Domain adaptation is proposed to deal with the challenging problem where the probability distribution of the training source is different from the testing target. Recently, adversarial learning has become the dominating technique for domain adaptation. Usually, adversarial domain adaptation methods simultaneously train a feature learner and a domain discriminator to learn domain-invariant features. Accordingly, how to effectively train the domain-adversarial model to learn domain-invariant features becomes a challenge in the community. To this end, we propose in this article a novel domain adaptation scheme named adversarial entropy optimization (AEO) to address the challenge. Specifically, we minimize the entropy when samples are from the independent distributions of source domain or target domain to improve the discriminability of the model. At the same time, we maximize the entropy when features are from the combined distribution of source domain and target domain so that the domain discriminator can be confused and the transferability of representations can be promoted. This minimax regime is well matched with the core idea of adversarial learning, empowering our model with transferability as well as discriminability for domain adaptation tasks. Also, AEO is flexible and compatible with different deep networks and domain adaptation frameworks. Experiments on five data sets show that our method can achieve state-of-the-art performance across diverse domain adaptation tasks.

Spatial graph convolutional neural network via structured subdomain adaptation and domain adversarial learning for bearing fault diagnosis

Unsupervised domain adaptation (UDA) has shown remarkable results in fault diagnosis under changing working conditions in recent years. However, most UDA methods do not consider the geometric structure of the data. Furthermore, the global domain adaptation technique is commonly applied, which ignores the relation between subdomains. This paper addresses mentioned challenges by presenting the novel deep subdomain adaptation graph convolution neural network (DSAGCN), which has two key characteristics: First, a graph convolution neural network (GCNN) is employed to model the structure of data. Second, adversarial domain adaptation and local maximum mean discrepancy (LMMD) methods are applied concurrently to align the subdomain’s distribution and reduce structure discrepancy between relevant subdomains and global domains. CWRU, PU, and JNU bearing datasets are used to validate the DSAGCN method’s superiority between comparison models. The experimental results demonstrate the significance of aligning structured subdomains along with domain adaptation methods to obtain an accurate data-driven model.

Multiple Adversarial Domains Adaptation Approach for Mitigating Adversarial Attacks Effects

Although neural networks are near achieving performance similar to humans in many tasks, they are susceptible to adversarial attacks in the form of a small, intentionally designed perturbation, which could lead to misclassifications. The best defense against these attacks, so far, is adversarial training (AT), which improves a model’s robustness by augmenting the training data with adversarial examples. However, AT usually decreases the model’s accuracy on clean samples and could overfit to a specific attack, inhibiting its ability to generalize to new attacks. In this paper, we investigate the usage of domain adaptation to enhance AT’s performance. We propose a novel multiple adversarial domain adaptation (MADA) method, which looks at this problem as a domain adaptation task to discover robust features. Specifically, we use adversarial learning to learn features that are domain-invariant between multiple adversarial domains and the clean domain. We evaluated MADA on MNIST and CIFAR-10 datasets with multiple adversarial attacks during training and testing. The results of our experiments show that MADA is superior to AT on adversarial samples by about 4% on average and on clean samples by about 1% on average.