Unsupervised Domain Adaptation With Adversarial Residual Transform Networks

Unsupervised Domain Adaptation for Low-Dose CT Reconstruction via Bayesian Uncertainty Alignment

Low-dose computed tomography (LDCT) image reconstruction techniques can reduce patient radiation exposure while maintaining acceptable imaging quality. Deep learning (DL) is widely used in this problem, but the performance of testing data (also known as target domain) is often degraded in clinical scenarios due to the variations that were not encountered in training data (also known as source domain). Unsupervised domain adaptation (UDA) of LDCT reconstruction has been proposed to solve this problem through distribution alignment. However, existing UDA methods fail to explore the usage of uncertainty quantification, which is crucial for reliable intelligent medical systems in clinical scenarios with unexpected variations. Moreover, existing direct alignment for different patients would lead to content mismatch issues. To address these issues, we propose to leverage a probabilistic reconstruction framework to conduct a joint discrepancy minimization between source and target domains in both the latent and image spaces. In the latent space, we devise a Bayesian uncertainty alignment to reduce the epistemic gap between the two domains. This approach reduces the uncertainty level of target domain data, making it more likely to render well-reconstructed results on target domains. In the image space, we propose a sharpness-aware distribution alignment (SDA) to achieve a match of second-order information, which can ensure that the reconstructed images from the target domain have similar sharpness to normal-dose CT (NDCT) images from the source domain. Experimental results on two simulated datasets and one clinical low-dose imaging dataset show that our proposed method outperforms other methods in quantitative and visualized performance.

Spatiotemporal Transformation-Based Neural Network With Interpretable Structure for Modeling Distributed Parameter Systems

Many industrial processes can be described by distributed parameter systems (DPSs) governed by partial differential equations (PDEs). In this research, a spatiotemporal network is proposed for DPS modeling without any process knowledge. Since traditional linear modeling methods may not work well for nonlinear DPSs, the proposed method considers the nonlinear space-time separation, which is transformed into a Lagrange dual optimization problem under the orthogonal constraint. The optimization problem can be solved by the proposed neural network with good structural interpretability. The spatial construction method is employed to derive the continuous spatial basis functions (SBFs) based on the discrete spatial features. The nonlinear temporal model is derived by the Gaussian process regression (GPR). Benefiting from spatial construction and GPR, the proposed method enables spatially continuous modeling and provides a reliable output range under the given confidence level. Experiments on a catalytic reaction process and a battery thermal process demonstrate the effectiveness and superiority of the proposed method.

Domain Adaptation via Prompt Learning

Unsupervised domain adaptation (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approaches learn domain-invariant features by aligning source and target feature spaces through statistical discrepancy minimization or adversarial training. However, these constraints could lead to the distortion of semantic feature structures and loss of class discriminability. In this article, we introduce a novel prompt learning paradigm for UDA, named domain adaptation via prompt learning (DAPrompt). In contrast to prior works, our approach learns the underlying label distribution for target domain rather than aligning domains. The main idea is to embed domain information into prompts, a form of representation generated from natural language, which is then used to perform classification. This domain information is shared only by images from the same domain, thereby dynamically adapting the classifier according to each domain. By adopting this paradigm, we show that our model not only outperforms previous methods on several cross-domain benchmarks but also is very efficient to train and easy to implement.

Dark-DSAR: Lightweight one-step pipeline for action recognition in dark videos

Dark video human action recognition has a wide range of applications in the real world. General action recognition methods focus on the actor or the action itself, ignoring the dark scene where the action happens, resulting in unsatisfied accuracy in recognition. For dark scenes, the existing two-step action recognition methods are stage complex due to introducing additional augmentation steps, and the one-step pipeline method is not lightweight enough. To address these issues, a one-step Transformer-based method named Dark Domain Shift for Action Recognition (Dark-DSAR) is proposed in this paper, which integrates the tasks of domain migration and classification into a single step and enhances the model's functional coherence with respect to these two tasks, making our Dark-DSAR has low computation but high accuracy. Specifically, the domain shift module (DSM) achieves domain adaption from dark to bright to reduce the number of parameters and the computational cost. Besides, we explore the matching relationship between the input video size and the model, which can further optimize the inference efficiency by removing the redundant information in videos through spatial resolution dropping. Extensive experiments have been conducted on the datasets of ARID1.5, HMDB51-Dark, and UAV-human-night. Results show that the proposed Dark-DSAR obtains the best Top-1 accuracy on ARID1.5 with 89.49%, which is 2.56% higher than the state-of-the-art method, 67.13% and 61.9% on HMDB51-Dark and UAV-human-night, respectively. In addition, ablation experiments reveal that the action classifiers can gain ≥1% in accuracy compared to the original model when equipped with our DSM.

Bridging the gap: Geometry-centric discriminative manifold distribution alignment for enhanced classification in colorectal cancer imaging

The early detection of colorectal cancer (CRC) through medical image analysis is a pivotal concern in healthcare, with the potential to significantly reduce mortality rates. Current Domain Adaptation (DA) methods strive to mitigate the discrepancies between different imaging modalities that are critical in identifying CRC, yet they often fall short in addressing the complexity of cancer's presentation within these images. These conventional techniques typically overlook the intricate geometrical structures and the local variations within the data, leading to suboptimal diagnostic performance. This study introduces an innovative application of the Discriminative Manifold Distribution Alignment (DMDA) method, which is specifically engineered to enhance the medical image diagnosis of colorectal cancer. DMDA transcends traditional DA approaches by focusing on both local and global distribution alignments and by intricately learning the intrinsic geometrical characteristics present in manifold space. This is achieved without depending on the potentially misleading pseudo-labels, a common pitfall in existing methodologies. Our implementation of DMDA on three distinct datasets, involving several unique DA tasks, has consistently demonstrated superior classification accuracy and computational efficiency. The method adeptly captures the complex morphological and textural nuances of CRC lesions, leading to a significant leap in domain adaptation technology. DMDA's ability to reconcile global and local distributional disparities, coupled with its manifold-based geometrical structure learning, signals a paradigm shift in medical imaging analysis. The results obtained are not only promising in terms of advancing domain adaptation theory but also in their practical implications, offering the prospect of substantially improved diagnostic accuracy and faster clinical workflows. This heralds a transformative approach in personalized oncology care, aligning with the pressing need for early and accurate CRC detection.

Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma

Artificial intelligence (AI) systems have been shown to help dermatologists diagnose melanoma more accurately, however they lack transparency, hindering user acceptance. Explainable AI (XAI) methods can help to increase transparency, yet often lack precise, domain-specific explanations. Moreover, the impact of XAI methods on dermatologists' decisions has not yet been evaluated. Building upon previous research, we introduce an XAI system that provides precise and domain-specific explanations alongside its differential diagnoses of melanomas and nevi. Through a three-phase study, we assess its impact on dermatologists' diagnostic accuracy, diagnostic confidence, and trust in the XAI-support. Our results show strong alignment between XAI and dermatologist explanations. We also show that dermatologists' confidence in their diagnoses, and their trust in the support system significantly increase with XAI compared to conventional AI. This study highlights dermatologists' willingness to adopt such XAI systems, promoting future use in the clinic.

MetaGeo: A General Framework for Social User Geolocation Identification With Few-Shot Learning

Identifying the geolocation of social media users is an important problem in a wide range of applications, spanning from disease outbreaks, emergency detection, local event recommendation, to fake news localization, online marketing planning, and even crime control and prevention. Researchers have attempted to propose various models by combining different sources of information, including text, social relation, and contextual data, which indeed has achieved promising results. However, existing approaches still suffer from certain constraints, such as: 1) a very few samples are available and 2) prediction models are not easy to be generalized for users from new regions-which are challenges that motivate our study. In this article, we propose a general framework for identifying user geolocation-MetaGeo, which is a meta-learning-based approach, learning the prior distribution of the geolocation task in order to quickly adapt the prediction toward users from new locations. Different from typical meta-learning settings that only learn a new concept from few-shot samples, MetaGeo improves the geolocation prediction with conventional settings by ensembling numerous mini-tasks. In addition, MetaGeo incorporates probabilistic inference to alleviate two issues inherent in training with few samples: location uncertainty and task ambiguity. To demonstrate the effectiveness of MetaGeo, we conduct extensive experimental evaluations on three real-world datasets and compare the performance with several state-of-the-art benchmark models. The results demonstrate the superiority of MetaGeo in both the settings where the predicted locations/regions are known or have not been seen during training.

Domain Adaptation as Optimal Transport on Grassmann Manifolds

Domain adaptation in the Euclidean space is a challenging task on which researchers recently have made great progress. However, in practice, there are rich data representations that are not Euclidean. For example, many high-dimensional data in computer vision are in general modeled by a low-dimensional manifold. This prompts the demand of exploring domain adaptation between non-Euclidean manifold spaces. This article is concerned with domain adaption over the classic Grassmann manifolds. An optimal transport-based domain adaptation model on Grassmann manifolds has been proposed. The model implements the adaption between datasets by minimizing the Wasserstein distances between the projected source data and the target data on Grassmann manifolds. Four regularization terms are introduced to keep task-related consistency in the adaptation process. Furthermore, to reduce the computational cost, a simplified model preserving the necessary adaption property and its efficient algorithm is proposed and tested. The experiments on several publicly available datasets prove the proposed model outperforms several relevant baseline domain adaptation methods.

Residual Tuning: Toward Novel Category Discovery Without Labels

Discovering novel visual categories from a set of unlabeled images is a crucial and essential capability for intelligent vision systems since it enables them to automatically learn new concepts with no need for human-annotated supervision anymore. To tackle this problem, existing approaches first pretrain a neural network with a set of labeled images and then fine-tune the network to cluster unlabeled images into a few categorical groups. However, their unified feature representation hits a tradeoff bottleneck between feature preservation on labeled data and feature adaptation on unlabeled data. To circumvent this bottleneck, we propose a residual-tuning approach, which estimates a new residual feature from the pretrained network and adds it with a previous basic feature to compute the clustering objective together. Our disentangled representation approach facilitates adjusting visual representations for unlabeled images and overcoming forgetting old knowledge acquired from labeled images, with no need of replaying the labeled images again. In addition, residual-tuning is an efficient solution, adding few parameters and consuming modest training time. Our results on three common benchmarks show consistent and considerable gains over other state-of-the-art methods, and further reduce the performance gap to the fully supervised learning setup. Moreover, we explore two extended scenarios, including using fewer labeled classes and continually discovering more unlabeled sets, where the results further signify the advantages and effectiveness of our residual-tuning approach against previous approaches. Our code is available at https://github.com/liuyudut/ResTune.

Scalable Gamma-Driven Multilayer Network for Brain Workload Detection Through Functional Near-Infrared Spectroscopy

This work proposes a scalable gamma non-negative matrix network (SGNMN), which uses a Poisson randomized Gamma factor analysis to obtain the neurons of the first layer of a network. These neurons obey Gamma distribution whose shape parameter infers the neurons of the next layer of the network and their related weights. Upsampling the connection weights follows a Dirichlet distribution. Downsampling hidden units obey Gamma distribution. This work performs up-down sampling on each layer to learn the parameters of SGNMN. Experimental results indicate that the width and depth of SGNMN are closely related, and a reasonable network structure for accurately detecting brain fatigue through functional near-infrared spectroscopy can be obtained by considering network width, depth, and parameters.

Prototype-Based Multisource Domain Adaptation

Unsupervised domain adaptation aims to transfer knowledge from labeled source domain to unlabeled target domain. Recently, multisource domain adaptation (MDA) has begun to attract attention. Its performance should go beyond simply mixing all source domains together for knowledge transfer. In this article, we propose a novel prototype-based method for MDA. Specifically, for solving the problem that the target domain has no label, we use the prototype to transfer the semantic category information from source domains to target domain. First, a feature extraction network is applied to both source and target domains to obtain the extracted features from which the domain-invariant features and domain-specific features will be disentangled. Then, based on these two kinds of features, the named inherent class prototypes and domain prototypes are estimated, respectively. Then a prototype mapping to the extracted feature space is learned in the feature reconstruction process. Thus, the class prototypes for all source and target domains can be constructed in the extracted feature space based on the previous domain prototypes and inherent class prototypes. By forcing the extracted features are close to the corresponding class prototypes for all domains, the feature extraction network is progressively adjusted. In the end, the inherent class prototypes are used as a classifier in the target domain. Our contribution is that through the inherent class prototypes and domain prototypes, the semantic category information from source domains is transformed into the target domain by constructing the corresponding class prototypes. In our method, all source and target domains are aligned twice at the feature level for better domain-invariant features and more closer features to the class prototypes, respectively. Several experiments on public data sets also prove the effectiveness of our method.

Decision-Tree-Initialized Dendritic Neuron Model for Fast and Accurate Data Classification

This work proposes a decision tree (DT)-based method for initializing a dendritic neuron model (DNM). Neural networks become larger and larger, thus consuming more and more computing resources. This calls for a strong need to prune neurons that do not contribute much to their network's output. Pruning those with low contribution may lead to a loss of accuracy of DNM. Our proposed method is novel because 1) it can reduce the number of dendrites in DNM while improving training efficiency without affecting accuracy and 2) it can select proper initialization weight and threshold of neurons. The Adam algorithm is used to train DNM after its initialization with our proposed DT-based method. To verify its effectiveness, we apply it to seven benchmark datasets. The results show that decision-tree-initialized DNM is significantly better than the original DNM, k-nearest neighbor, support vector machine, back-propagation neural network, and DT classification methods. It exhibits the lowest model complexity and highest training speed without losing any accuracy. The interactions among attributes can also be observed in its dendritic neurons.

Online Unsupervised Domain Adaptation via Reducing Inter- and Intra-Domain Discrepancies

Unsupervised domain adaptation (UDA) transfers knowledge from a labeled source domain to an unlabeled target domain on cross-domain object recognition by reducing a distribution discrepancy between the source and target domains (interdomain discrepancy). Prevailing methods on UDA were presented based on the premise that target data are collected in advance. However, in online scenarios, the target data often arrive in a streamed manner, such as visual image recognition in daily monitoring, which means that there is a distribution discrepancy between incoming target data and collected target data (intradomain discrepancy). Consequently, most existing methods need to re-adapt the incoming data and retrain a new model on online data. This paradigm is difficult to meet the real-time requirements of online tasks. In this study, we propose an online UDA framework via jointly reducing interdomain and intradomain discrepancies on cross-domain object recognition where target data arrive in a streamed manner. Specifically, the proposed framework comprises two phases: classifier training and online recognition phases. In the former, we propose training a classifier on a shared subspace where there is a lower interdomain discrepancy between the two domains. In the latter, a low-rank subspace alignment method is introduced to adapt incoming data to the shared subspace by reducing the intradomain discrepancy. Finally, online recognition results can be obtained by the trained classifier. Extensive experiments on DA benchmarks and real-world datasets are employed to evaluate the performance of the proposed framework in online scenarios. The experimental results show the superiority of the proposed framework in online recognition tasks.

Dynamic Embedding Projection-Gated Convolutional Neural Networks for Text Classification

Text classification is a fundamental and important area of natural language processing for assigning a text into at least one predefined tag or category according to its content. Most of the advanced systems are either too simple to get high accuracy or centered on using complex structures to capture the genuinely required category information, which requires long time to converge during their training stage. In order to address such challenging issues, we propose a dynamic embedding projection-gated convolutional neural network (DEP-CNN) for multi-class and multi-label text classification. Its dynamic embedding projection gate (DEPG) transforms and carries word information by using gating units and shortcut connections to control how much context information is incorporated into each specific position of a word-embedding matrix in a text. To our knowledge, we are the first to apply DEPG over a word-embedding matrix. The experimental results on four known benchmark datasets display that DEP-CNN outperforms its recent peers.

Effective Visual Domain Adaptation via Generative Adversarial Distribution Matching

In the field of computer vision, without sufficient labeled images, it is challenging to train an accurate model. However, through visual adaptation from source to target domains, a relevant labeled dataset can help solve such problem. Many methods apply adversarial learning to diminish cross-domain distribution difference. They are able to greatly enhance the performance on target classification tasks. Generative adversarial network (GAN) loss is widely used in adversarial adaptation learning methods to reduce an across-domain distribution difference. However, it becomes difficult to decline such distribution difference if generator or discriminator in GAN fails to work as expected and degrades its performance. To solve such cross-domain classification problems, we put forward a novel adaptation framework called generative adversarial distribution matching (GADM). In GADM, we improve the objective function by taking cross-domain discrepancy distance into consideration and further minimize the difference through the competition between a generator and discriminator, thereby greatly decreasing cross-domain distribution difference. Experimental results and comparison with several state-of-the-art methods verify GADM's superiority in image classification across domains.

Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems

Data-driven models are becoming essential parts in modern mechanical systems, commonly used to capture the behavior of various equipment and varying environmental characteristics. Despite the advantages of these data-driven models on excellent adaptivity to high dynamics and aging equipment, they are usually hungry for massive labels, mostly contributed by human engineers at a high cost. Fortunately, domain adaptation enhances the model generalization by utilizing the labeled source data and the unlabeled target data. However, the mainstream domain adaptation methods cannot achieve ideal performance on time series data, since they assume that the conditional distributions are equal. This assumption works well in the static data but is inapplicable for the time series data. Even the first-order Markov dependence assumption requires the dependence between any two consecutive time steps. In this article, we assume that the causal mechanism is invariant and present our Causal Mechanism Transfer Network (CMTN) for time series domain adaptation. By capturing causal mechanisms of time series data, CMTN allows the data-driven models to exploit existing data and labels from similar systems, such that the resulting model on a new system is highly reliable even with limited data. We report our empirical results and lessons learned from two real-world case studies, on chiller plant energy optimization and boiler fault detection, which outperform the existing state-of-the-art method.

Subspace Distribution Adaptation Frameworks for Domain Adaptation

Domain adaptation tries to adapt a model trained from a source domain to a different but related target domain. Currently, prevailing methods for domain adaptation rely on either instance reweighting or feature transformation. Unfortunately, instance reweighting has difficulty in estimating the sample weights as the dimension increases, whereas feature transformation sometimes fails to make the transformed source and target distributions similar when the cross-domain discrepancy is large. In order to overcome the shortcomings of both methodologies, in this article, we model the unsupervised domain adaptation problem under the generalized covariate shift assumption and adapt the source distribution to the target distribution in a subspace by applying a distribution adaptation function. Accordingly, we propose two frameworks: Bregman-divergence-embedded structural risk minimization (BSRM) and joint structural risk minimization (JSRM). In the proposed frameworks, the subspace distribution adaptation function and the target prediction model are jointly learned. Under certain instantiations, convex optimization problems are derived from both frameworks. Experimental results on the synthetic and real-world text and image data sets show that the proposed methods outperform the state-of-the-art domain adaptation techniques with statistical significance.

DACH: Domain Adaptation Without Domain Information

Domain adaptation is becoming increasingly important for learning systems in recent years, especially with the growing diversification of data domains in real-world applications, such as the genetic data from various sequencing platforms and video feeds from multiple surveillance cameras. Traditional domain adaptation approaches target to design transformations for each individual domain so that the twisted data from different domains follow an almost identical distribution. In many applications, however, the data from diversified domains are simply dumped to an archive even without clear domain labels. In this article, we discuss the possibility of learning domain adaptations even when the data does not contain domain labels. Our solution is based on our new model, named domain adaption using cross-domain homomorphism (DACH in short), to identify intrinsic homomorphism hidden in mixed data from all domains. DACH is generally compatible with existing deep learning frameworks, enabling the generation of nonlinear features from the original data domains. Our theoretical analysis not only shows the universality of the homomorphism, but also proves the convergence of DACH for significant homomorphism structures over the data domains is preserved. Empirical studies on real-world data sets validate the effectiveness of DACH on merging multiple data domains for joint machine learning tasks and the scalability of our algorithm to domain dimensionality.

Single Image De-Raining via Improved Generative Adversarial Nets

Capturing images under rainy days degrades image visual quality and affects analysis tasks, such as object detection and classification. Therefore, image de-raining has attracted a lot of attention in recent years. In this paper, an improved generative adversarial network for single image de-raining is proposed. According to the principles of divide-and-conquer, we divide an image de-raining task into rain locating, rain removing, and detail refining sub-tasks. A multi-stream DenseNet, termed as Rain Estimation Network, is proposed to estimate the rain location map. A Generative Adversarial Network is proposed to remove the rain streaks. A Refinement Network is proposed to refine the details. These three models accomplish rain locating, rain removing, and detail refining sub-tasks, respectively. Experiments on two synthetic datasets and real world images demonstrate that the proposed method outperforms state-of-the-art de-raining studies in both objective and subjective measurements.