S-CUDA: Self-cleansing unsupervised domain adaptation for medical image segmentation.

Accurate segmentation of the optic disc and cup (OD/OC) in fundus images is crucial for the glaucoma diagnosis and treatment. However, the distribution discrepancies (domain shift) between source domain and target domain hinder the generalization of segmentation models in clinical applications. In this paper, a dual gradient alignment framework (DGDA) for unsupervised domain adaptation is proposed to achieve accurate OD/OC segmentation. Specifically, feature gradient alignment module is well-designed to learn the domain-invariant representation by aligning the feature gradients between source and target domains. Furthermore, task gradient alignment module introduces the meta-learning to learn the task-agnostic representation to simultaneously balance domain adaptation and OD/OC segmentation. Here, meta-learning imitates multi-task training by aligning the gradients between the segmentation and domain classification task. Extensive experiments are conducted on the two public fundus image datasets (Drishti-GS and RIM-ONE-r3) to evaluate the effectiveness of the proposed DGDA. Experimental results demonstrate the DGDA successfully achieves the unsupervised domain adaptive OD/OC segmentation with competitive performance compared with the state-of-the-art.

Segmenting the optic disc (OD) and optic cup (OC) is crucial to accurately detect changes in glaucoma progression in the elderly. Recently, various convolutional neural networks have emerged to deal with OD and OC segmentation. Due to the domain shift problem, achieving high-accuracy segmentation of OD and OC from different domain datasets remains highly challenging. Unsupervised domain adaptation has taken extensive focus as a way to address this problem. In this work, we propose a novel unsupervised domain adaptation method, called entropy and distance-guided super self-ensembling (EDSS), to enhance the segmentation performance of OD and OC. EDSS is comprised of two self-ensembling models, and the Gaussian noise is added to the weights of the whole network. Firstly, we design a super self-ensembling (SSE) framework, which can combine two self-ensembling to learn more discriminative information about images. Secondly, we propose a novel exponential moving average with Gaussian noise (G-EMA) to enhance the robustness of the self-ensembling framework. Thirdly, we propose an effective multi-information fusion strategy (MFS) to guide and improve the domain adaptation process. We evaluate the proposed EDSS on two public fundus image datasets RIGA+ and REFUGE. Large amounts of experimental results demonstrate that the proposed EDSS outperforms state-of-the-art segmentation methods with unsupervised domain adaptation, e.g., the Dicemean score on three test sub-datasets of RIGA+ are 0.8442, 0.8772 and 0.9006, respectively, and the Dicemean score on the REFUGE dataset is 0.9154.

Bionic limb control through myoelectric pattern recognition, offering intuitive decoding of motor intent, can improve the quality of life for individuals with amputations. However, most work on pattern recognition only uses a small subset of the myoelectric data generated during daily life, to train an Artificial Neural Network (ANN) via Supervised Learning (SL). Scenarios substantially different from the recording session e.g. different limb positions, can lead to misclassifications by the ANN during everyday usage of the bionic limb. Recording labeled data from all scenarios encountered in daily life could alleviate the problem, but would be prohibitively time consuming. Unsupervised Domain Adaptation (UDA) offers a solution by leveraging unlabeled data from a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">target domain</i>, not represented in the labeled dataset i.e. the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">source domain</i>, to calibrate ANNs for improved performance. In this study we explore the potential of two UDA algorithms for domain shifts in myoelectric pattern recognition: Domain Adversarial Neural Networks (DANN) and Sliced Wasserstein Discrepancy (SWD). Offline evaluation identified SWD as the best-performing algorithm, which was subsequently validated in online experiments with 11 participants. Using UDA improved the performance on the target domain by 19% compared to an ANN trained through SL on data from the source domain only. Indeed, it nearly matched the performance of an ANN trained through SL on labeled data from both the source and target domain. This is the first time UDA was validated in online experiments as a viable approach to overcome domain shift problems caused by changes in limb position.

Domain consistency regularization for unsupervised multi-source domain adaptive classification

Detecting frauds in computing platforms involves identifying malicious user activity sessions. Recently, deep learning models have been employed to design fraud detection approaches. Effective training of these deep learning models requires a large amount of well-annotated sessions. However, due to the cost of expert annotation, many organizations rely on heuristics to perform automated annotation, which leads to the noisy label learning problem. It is well known that the performance of deep learning models can easily degrade because of noisy or inaccurate labels. To tackle this challenge, we propose a supervised Contrastive Learning based Fraud Detection (CLFD) framework, which is designed to operate in the noisy label setting. CLFD employs an effective label corrector for correcting noisy labels and which is specifically designed for the fraud detection task. Then, by employing the corrected labels, it trains a fraud detector through supervised contrastive learning, and derives separable representations. We empirically evaluate our CLFD framework and other state-of-the-art baselines on benchmark datasets. Our CLFD framework demonstrates superior performance over state-of-the-art baselines.

With the rapid development of the remote sensing monitoring and computer vision technology, the deep learning method has made a great progress to achieve applications such as earth observation, climate change and even space exploration. However, the model trained on existing data cannot be directly used to handle the new remote sensing data, and labeling the new data is also time-consuming and labor-intensive. Unsupervised Domain Adaptation (UDA) is one of the solutions to the aforementioned problems of labeled data defined as the source domain and unlabeled data as the target domain, i.e., its essential purpose is to obtain a well-trained model and tackle the problem of data distribution discrepancy defined as the domain shift between the source and target domain. There are a lot of reviews that have elaborated on UDA methods based on natural data, but few of these studies take into consideration thorough remote sensing applications and contributions. Thus, in this paper, in order to explore the further progress and development of UDA methods in remote sensing, based on the analysis of the causes of domain shift, a comprehensive review is provided with a fine-grained taxonomy of UDA methods applied for remote sensing data, which includes Generative training, Adversarial training, Self-training and Hybrid training methods, to better assist scholars in understanding remote sensing data and further advance the development of methods. Moreover, remote sensing applications are introduced by a thorough dataset analysis. Meanwhile, we sort out definitions and methodology introductions of partial, open-set and multi-domain UDA, which are more pertinent to real-world remote sensing applications. We can draw the conclusion that UDA methods in the field of remote sensing data are carried out later than those applied in natural images, and due to the domain gap caused by appearance differences, most of methods focus on how to use generative training (GT) methods to improve the model’s performance. Finally, we describe the potential deficiencies and further in-depth insights of UDA in the field of remote sensing.

Unsupervised deep domain adaptation algorithm for video based human activity recognition via recurrent neural networks

Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. However, such an assumption is rarely plausible in the real world and possibly causes data privacy issues, especially when the label of the source domain can be a sensitive attribute as an identifier. To avoid accessing source data that could contain sensitive information, we introduce source data free domain adaptation (SFDA). Our key idea is to leverage a pretrained model from the source domain and progressively update the target model in a self-learning manner. We observe that target samples with lower self-entropy measured by the pretrained source model are more likely to be classified correctly. From this, we select the reliable samples with the self-entropy criterion and define these as class prototypes. We then assign pseudolabels for every target sample based on the similarity score with class prototypes. We further propose point-to-set distance-based filtering, which does not require any tunable hyperparameters to reduce uncertainty from the pseudolabeling process. Finally, we train the target model with the filtered pseudolabels with regularization from the pretrained source model. Surprisingly, without direct usage of labeled source samples, our SFDA outperforms conventional domain adaptation methods on benchmark datasets. <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b><i>Impact Statement</i></b>—This study addresses the data privacy issue, especially in unsupervised domain adaptation. Based on our privacy-preserving domain adaptation, various stakeholders, including enterprises and government organizations, can be free of concern about privacy issues with their labeled source dataset. Furthermore, the proposed data-free approach can contribute to creating a positive social impact, especially in large-scale datasets. Recently, since the size of data across various fields has been scaling up, it is almost incapable for individual researchers to directly utilize a large scale of data during training. For this reason, a new social trend of sharing pretrained models, e.g., EfficientNet and BERT, led by global enterprises with their huge amount of resources has been rising up. From this viewpoint, our approach thus enables more people to participate in the domain adaptation field specifically when the source data are large scale and contain sensitive attributes.

This work addresses the challenge of video violence detection in data-scarce scenarios, focusing on bridging the domain gap that often hinders the performance of deep learning models when applied to unseen domains. We present a novel unsupervised domain adaptation (UDA) scheme designed to effectively mitigate this gap by combining supervised learning in the train (source) domain with unlabeled test (target) data. We employ single-image classification and multiple instance learning (MIL) to select frames with the highest classification scores, and, upon this, we exploit UDA techniques to adapt the model to unlabeled target domains. We perform an extensive experimental evaluation, using general-context data as the source domain and target domain datasets collected in specific environments, such as violent/non-violent actions in hockey matches and public transport. The results demonstrate that our UDA pipeline substantially enhances model performances, improving their generalization capabilities in novel scenarios without requiring additional labeled data.

With abundant labeled data, deep convolutional neural networks have shown great success in various image recognition tasks. However, these models are often less powerful when applied to novel datasets due to a phenomenon known as domain shift. Unsupervised domain adaptation methods aim to address this problem, allowing deep models trained on the labeled source domain to be used on a different target domain (without labels). In this presentation, we investigate whether the generalization ability of an unsupervised domain adaptation method can be improved through multi-task learning, with learned features required to be both domain invariant and discriminative for multiple different but relevant tasks. Experiments evaluating two fundamental recognition tasks---image recognition and segmentation---show that the generalization ability empowered by multi-task learning may not benefit recognition when the model is directly applied on the target domain, but the multi-task learning setting can boost the performance of state-of-the-art unsupervised domain adaptation methods by a non-negligible margin.

Recently, a particular paradigm [18] in the domain adaptation field has received considerable attention by introducing novel and important insights to the problem. In this case, the source and target domains are represented in the form of subspaces, which are treated as points on the Grassmann manifold. The geodesic curve between them is sampled to obtain intermediate points. Then a classifier is learnt using the projections of the data onto these subspaces. Despite its relevance and popularity, this paradigm [18] contains some limitations. Firstly, in real-world applications, that simple curve (i.e. shortest path) does not provide the necessary flexibility to model the domain shift between the training and testing data sets. Secondly, by using the geodesic curve, we are restricted to only one source domain, which does not allow to take fully advantage of the multiple datasets that are available nowadays. It is then, natural to ask whether this popular concept could be extended to deal with more complex curves and to integrate multi-sources domains. This is a hard problem considering the Riemannian structure of the space, but we propose a mathematically well-founded idea that enables us to solve it. We exploit the geometric insight of rolling maps [30] to compute a spline curve on the Grassmann manifold. The benefits of the proposed idea are demonstrated through several empirical studies on standard datasets. This novel concept allows to explicitly integrate multi-source domains while the previous one [18] uses the mean of all sources. This enables to model better the domain shift and take fully advantage of the training datasets.

When deep neural networks are deployed in a highly automated vehicle for environment perception tasks in an unseen (target) domain that differs from the training (source) domain, the mismatch will result in decreased performance. Domain adaptation methods aim at overcoming this mismatch. Many recently investigated methods for unsupervised domain adaptation train a model using labeled source data and unlabeled target data at the same time. These methods assume that data from the target domain is available during the source domain training, which is not always the case in real applications. In this paper we present a way to perform an online style transfer for continual domain adaptation which improves performance on (multiple) unseen target domains using a given perception model. The approach is based on an image style transfer in the frequency domain and requires neither an adjustment of the given source-trained model parameters to the target domain, nor does it require any considerable amount of memory for storing its frequency domain representation of the source domain style, which is particularly important considering the hardware limitations in an autonomous vehicle.

Supervised learning methods require sufficient labeled examples to learn a good model for classification or regression. However, available labeled data are insufficient in many applications. Active learning (AL) and domain adaptation (DA) are two strategies to minimize the required amount of labeled data for model training. AL requires the domain expert to label a small number of highly informative examples to facilitate classification, while DA involves tuning the source domain knowledge for classification on the target domain. In this paper, we demonstrate how AL can efficiently minimize the required amount of labeled data for DA. Since the source and target domains usually have different distributions, it is possible that the domain expert may not have sufficient knowledge to answer each query correctly. We exploit our active DA framework to handle incorrect labels provided by domain experts. Experiments with multimedia data demonstrate the efficiency of our proposed framework for active DA with noisy labels.

The prime challenge in unsupervised domain adaptation (DA) is to mitigate the domain shift between the source and target domains. Prior DA works show that pretext tasks could be used to mitigate this domain shift by learning domain invariant representations. However, in practice, we find that most existing pretext tasks are ineffective against other established techniques. Thus, we theoretically analyze how and when a subsidiary pretext task could be leveraged to assist the goal task of a given DA problem and develop objective subsidiary task suitability criteria. Based on this criteria, we devise a novel process of sticker intervention and cast sticker classification as a supervised subsidiary DA problem concurrent to the goal task unsupervised DA. Our approach not only improves goal task adaptation performance, but also facilitates privacy-oriented source-free DA i.e. without concurrent source-target access. Experiments on the standard Office-31, Office-Home, DomainNet, and VisDA benchmarks demonstrate our superiority for both single-source and multi-source source-free DA. Our approach also complements existing non-source-free works, achieving leading performance.

Adaptive Cross Entropy for ultrasmall object detection in Computed Tomography with noisy labels