Target Instances Research Articles

Unsupervised domain adaptation using fuzzy rules and stochastic hierarchical convolutional neural networks

Unsupervised domain adaptation (UDA) describes a set of techniques for using previously acquired knowledge from labeled original data to support task completion in comparable but unlabeled target data. Existing UDA methods often use two classifiers to detect misaligned local areas between the original and prey vocations, resulting in poor implementation. To address this issue, we propose a fuzzy rules and stochastic classifier-based domain adaptation framework called SH-CNN+SMTEOA. Initially, the cross-domain mixed sampling approach is used to test the original and prey data. After that, the Principal Component Analysis is used to extract the characteristics, and fuzzy criteria are used to choose the suitable characteristics. Finally, we introduce the Stochastic Hierarchical Convolutional Neural Network for classification and the Selective Multi-Threshold Entropy Optimization Algorithm for judging a target instance’s dependability based on its predictive multi-threshold values. Investigations on UDA benchmark datasets reveal that the proposed method outperforms other methods in classification.

Knowledge-Based Representation Learning for Nucleus Instance Classification From Histopathological Images.

The classification of nuclei in H&E-stained histopathological images is a fundamental step in the quantitative analysis of digital pathology. Most existing methods employ multi-class classification on the detected nucleus instances, while the annotation scale greatly limits their performance. Moreover, they often downplay the contextual information surrounding nucleus instances that is critical for classification. To explicitly provide contextual information to the classification model, we design a new structured input consisting of a content-rich image patch and a target instance mask. The image patch provides rich contextual information, while the target instance mask indicates the location of the instance to be classified and emphasizes its shape. Benefiting from our structured input format, we propose Structured Triplet for representation learning, a triplet learning framework on unlabelled nucleus instances with customized positive and negative sampling strategies. We pre-train a feature extraction model based on this framework with a large-scale unlabeled dataset, making it possible to train an effective classification model with limited annotated data. We also add two auxiliary branches, namely the attribute learning branch and the conventional self-supervised learning branch, to further improve its performance. As part of this work, we will release a new dataset of H&E-stained pathology images with nucleus instance masks, containing 20,187 patches of size 1024 ×1024 , where each patch comes from a different whole-slide image. The model pre-trained on this dataset with our framework significantly reduces the burden of extensive labeling. We show a substantial improvement in nucleus classification accuracy compared with the state-of-the-art methods.

Cross-Domain Open-Set Machinery Fault Diagnosis Based on Adversarial Network With Multiple Auxiliary Classifiers

Cross-domain fault diagnosis methods based on transfer learning attempt to leverage knowledge from a domain with sufficient labeled samples to a different but related domain with few or even nonlabeled samples. These methods have been widely investigated in the past years. Notwithstanding the efficacy, most existing approaches assume that the label spaces of training and testing data are the same. However, this assumption is not practical in actual applications because new fault category usually happens in the testing stage. A cross-domain open-set transfer diagnosis method is presented in this article to manage the aforementioned problem. Domain adversarial model is employed to discriminate known from unknown target instances. Moreover, multiple auxiliary classifiers introduce a weighting module to evaluate the distinguishing domain knowledge to provide target instances with representative weights. The new adversarial domain adaptation network with diverse supplementary classifiers can effectively identify the unknown and known fault categories in the target domain and bridge the domain shift between the common fault category of the source and target domain. Experiments on two bearing datasets show the effectiveness and advantage of the proposed method.

A Latent Factor Analysis-Based Approach to Online Sparse Streaming Feature Selection

Online streaming feature selection (OSFS) has attracted extensive attention during the past decades. Current approaches commonly assume that the feature space of fixed data instances dynamically increases without any missing data. However, this assumption does not always hold in many real applications. Motivated by this observation, this study aims to implement online feature selection from sparse streaming features, i.e., features flow in one by one with missing data as instance count remains fixed. To do so, this study proposes a latent-factor-analysis-based online sparse-streaming-feature selection algorithm (LOSSA). Its main idea is to apply latent factor analysis to pre-estimate missing data in sparse streaming features before conducting feature selection, thereby addressing the missing data issue effectively and efficiently. Theoretical and empirical studies indicate that LOSSA can significantly improve the quality of OSFS when missing data are encountered in target instances.

Extending Partial Domain Adaptation Algorithms to the Open-Set Setting

Partial domain adaptation (PDA) is a framework for mitigating the covariate shift problem when target labels are contained in source labels. For this task, adversarial neural network (ANN) methods proposed in the literature have been proven to be flexible and effective. In this work, we adapt such methods to tackle the more general problem of open-set domain adaptation (OSDA), which further allows the existence of target instances with labels outside the source labels. The aim in OSDA is to mitigate the covariate shift problem and to identify target instances with labels outside the source label space. We show that the effectiveness of ANN methods utilized in the PDA setting is hindered by outlier target instances, and we propose an adaptation for effective OSDA.

Study of a QueryPNet Model for Accurate Detection and Segmentation of Goose Body Edge Contours.

Simple SummaryPrecision animal husbandry based on computer vision has developed promptly, especially in poultry farming. It is believed to improve animal welfare. To achieve the precise target detection and segmentation of geese, which can improve data acquisition, we newly built the world’s first goose instance segmentation dataset. Moreover, a high-precision detection and segmentation model was constructed, and the final mAP@0.5 of both target detection and segmentation reached 0.963. The evaluation of the model showed that the automated detection method proposed in this paper is feasible in a complex environment and can serve as a reference for the relevant development of the industry.With the rapid development of computer vision, the application of computer vision to precision farming in animal husbandry is currently a hot research topic. Due to the scale of goose breeding continuing to expand, there are higher requirements for the efficiency of goose farming. To achieve precision animal husbandry and to avoid human influence on breeding, real-time automated monitoring methods have been used in this area. To be specific, on the basis of instance segmentation, the activities of individual geese are accurately detected, counted, and analyzed, which is effective for achieving traceability of the condition of the flock and reducing breeding costs. We trained QueryPNet, an advanced model, which could effectively perform segmentation and extraction of geese flock. Meanwhile, we proposed a novel neck module that improved the feature pyramid structure, making feature fusion more effective for both target detection and instance individual segmentation. At the same time, the number of model parameters was reduced by a rational design. This solution was tested on 639 datasets collected and labeled on specially created free-range goose farms. With the occlusion of vegetation and litters, the accuracies of the target detection and instance segmentation reached 0.963 (mAP@0.5) and 0.963 (mAP@0.5), respectively.

Click-through rate prediction using transfer learning with fine-tuned parameters

In real business platforms, recommendation systems usually need to predict the CTR of multiple business. Since different scenarios may have common feature interactions, knowledge transferring based methods are often used by re-optimizing the pre-trained CTR model from source scenarios to a new target domain. In addition to knowledge transfer, it is noteworthy that generalizing target domain data outside of the CTR model accurately is also important when re-training all of the fine-tuned parameters. Generally, the pre-trained model trained on large source domains can represent the characteristics of different instances and capture typical feature interactions. It would be useful to directly reuse fine-tuned parameters from source domains to serve the target domain. However, different instances of the target domain may need different amounts of source information to fine-tune the model parameters, and these decisions of freezing or re-optimizing model parameters, which highly depend on the fine-tuned model and target instances, may require much manual effort. In this paper, we propose an end-to-end transfer learning framework with fine-tuned parameters for CTR prediction, called Automatic Fine-Tuning (AutoFT). The principal component of AutoFT is a set of learnable transfer policies that independently determine how the specific instance-based fine-tuning policies should be trained, which decide the routing in the embedding representations and the high-order feature representations layer by layer in deep CTR model. Extensive tests on two benchmarks and one real commercial recommender system deployed in Huawei's App Store show that AutoFT can greatly increase CTR prediction performance when compared to current transferring methodologies.

A weak prior embedding-based method for transfer fault diagnosis of rolling bearing

Transfer learning extends the application scope of deep intelligent fault diagnosis models. However, when operation conditions are significantly varied, existing transfer learning methods may encounter a bottleneck. The unsupervised methods will mismatch features, while supervised methods are constrained by insufficient target labeled instances. A weak prior embedding-based domain adaption network (WPEDAN) is proposed to resolve this problem. Specifically, the cluster ability of source data pre-trained network to target data is emphasized and enhanced directly and indirectly so as to obtain discriminative feature clusters. The target prior template samples are embedded and automatically delivered to the most relevant feature clusters, so the class information of target instances can be estimated based on similarity and supervised training on target is following. Moreover, an improved conditional maximum mean discrepancy (ICMMD) is developed to further align conditional distribution. Experiments on two challenging bearing datasets show that proposed method achieves more than 99% diagnosis accuracy in all tasks, and is significantly ahead of the comparison methods in complex transfer tasks.

Interactive dual adversarial neural network framework: An open-set domain adaptation intelligent fault diagnosis method of rotating machinery

The domain-adaptation technique has been proven to be able to resolve the fault diagnosis under various working conditions. Most research presumes that the health states in the source domain are consistent with the target domain. However, open-set domain adaptation problem that contains the unknown states in testing process remains unexplored. Here we propose an interactive dual adversarial neural network (IDANN) for this problem. First, a closed-set domain adversarial network is trained to obtain the weight of each target instance. Then, an open-set domain adversarial network is trained by importing the weighted unknown classification items and entropy minimization techniques. Through a series of interactive training, the IDANN can not only distinguish the unknown instances but also assign known instances to corresponding classes. Two experiment cases validate the effectiveness of the proposed IDANN method. The comparison results suggest that the proposed method can achieve superior performance in open-set domain adaptation problems.

Joint Domain Adaption and Pseudo-Labeling for Cross-Project Defect Prediction

Cross-project defect prediction (CPDP) is a hot research topic in recent years. The inconsistent data distribution between source and target projects and lack of labels for most of target instances bring a challenge for defect prediction. Researchers have developed several CPDP methods. However, the prediction performance still needs to be improved. In this paper, we propose a novel approach called Joint Domain Adaption and Pseudo-Labeling (JDAPL). The network architecture consists of a feature mapping sub-network to map source and target instances into a common subspace, followed by a classification sub-network and an auxiliary classification sub-network. The classification sub-network makes use of the label information of labeled instances to generate pseudo-labels. The auxiliary classification sub-network learns to reduce the distribution difference and improve the accuracy of pseudo-labels for unlabeled instances through loss maximization. Network training is guided by the adversarial scheme. Extensive experiments are conducted on 10 projects of the AEEEM and NASA datasets, and the results indicate that our approach achieves better performance compared with the baselines.

‘Tell me about the time you remember the best’: the effect of a remember best prompt on adults’ reports of a repeated emotionally stressful event

ABSTRACT In two experiments we investigated the effect of a ‘remember best’ prompt on recall of one instance of a repeated event. Adult female participants (N = 98 Experiment 1; N = 100 Experiment 2) engaged in imagined experiences of abusive relationship encounters on either one occasion (single group) or four occasions (repeat-last and repeat-best groups). Participants then completed a memory assessment for the target instance. In the single and repeat-last groups, participants recalled a pre-determined target instance (i.e. last instance for repeat-last group), while the repeat-best group self-selected which instance to discuss (i.e. the time they ‘remember best’). In Experiment 1, repeat-best participants selected an instance based on when it occurred, while in Experiment 2, participants identified and uniquely labelled the instance remembered best. Experiment 1 results revealed that the ‘remember best’ prompt was not effective in enhancing accurate retrieval of one instance, while the ‘remember best’ prompt in Experiment 2 did appear to enhance retrieval when compared to the control groups. These findings suggest that accurate retrieval of one instance of a repeated event might depend on how memory is cued. The forensic implications of these findings for testimonies of repeated abuse (e.g. domestic abuse) are discussed.

Knowledge transfer for causal discovery

Subject-specific causal discovery methods could help to make better decisions in domains where there are variations on causal relations across subjects, such as neuroscience and genetics. However, discovering subject-specific causal models from limited data sets could be challenging. Although there are several causal discovery methods, most of them are focused on finding the common causal relations of a population from data sets with enough samples. The issue of discovering subject-specific causal relations from limited data sets has not been sufficiently explored. In this paper, we propose a knowledge transfer method for discovering subject-specific causal models. Our method discovers causal probabilistic graphical models, up to Markov equivalence classes, from discrete and continuous data sets. We hypothesized that transferring weighted instances of additional sources according to their discrepancy with target instances helps to compensate for the lack of target data and improves the performance of a scored-based causal discovery method. Experimental results on synthetic data sets and benchmark causal Bayesian networks show that our proposal, under few target samples, outperforms significantly in adjacency and arrowhead recovery the baseline and alternative methods.

Learning Orientation Information From Frequency-Domain for Oriented Object Detection in Remote Sensing Images

Object detection in remote sensing images (RSIs) poses great difficulties due to arbitrary orientations, various scales and dense location of the targets over the ground. Recent evidence suggests that encoding the orientation information is of great use for training an accurate object detector for oriented object detection (OOD). In this paper, we propose a new frequency-domain orientation learning (FDOL) module with two main components: the frequency domain feature extraction (FFE) network and an orientation enhanced self-attention layer (OES-Layer). The FFE network models the interactions among spatial locations in the frequency domain to determine the frequency of spatial features. Then, these features are fed into our OES-Layer to learn the orientation information. Moreover, the orientation weights are adopted to guide the feature selection in a self-attention architecture, using them as a control gate to emphasize the spatial responses of target instances. Considering that the original similarity weights (calculated by the self-attention algorithm) do not distinctly model the orientation variation, the considered orientation weights provide an efficient asset to emphasize the orientation of objects. Extensive experiments on the DOTA and HRSC2016 datasets demonstrate that our method achieves state-of-the-art performance among single-scale methods, while achieving competitive performance over multi-scale methods.

Confident Learning-Based Domain Adaptation for Hyperspectral Image Classification

Cross-domain hyperspectral image classification is one of the major challenges in remote sensing, especially for target domain data without labels. Recently, deep learning approaches have demonstrated effectiveness in domain adaptation. However, most of them leverage unlabeled target data only from a statistical perspective but neglect the analysis at the instance level. For better statistical alignment, existing approaches employ the entire unevaluated target data in an unsupervised manner, which may introduce noise and limit the discriminability of the neural networks. In this article, we propose confident learning-based domain adaptation (CLDA) to address the problem from a new perspective of data manipulation. To this end, a novel framework is presented to combine domain adaptation with confident learning (CL), where the former reduces the interdomain discrepancy and generates pseudo-labels for the target instances, from which the latter selects high-confidence target samples. Specifically, the confident learning part evaluates the confidence of each pseudo-labeled target sample based on the assigned labels and the predicted probabilities. Then, high-confidence target samples are selected as training data to increase the discriminative capacity of the neural networks. In addition, the domain adaptation part and the confident learning part are trained alternately to progressively increase the proportion of high-confidence labels in the target domain, thus further improving the accuracy of classification. Experimental results on four datasets demonstrate that the proposed CLDA method outperforms the state-of-the-art domain adaptation approaches. Our source code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Li-ZK/CLDA-2022</uri> .

Bi-shifting semantic auto-encoder for zero-shot learning

&lt;abstract&gt;&lt;p&gt;Zero-shot learning aims to transfer the model of labeled seen classes in the source domain to the disjoint unseen classes without annotations in the target domain. Most existing approaches generally consider directly adopting the visual-semantic projection function learned in the source domain to the target domain without adaptation. However, due to the distribution discrepancy between the two domains, it remains challenging in dealing with the projection domain shift problem. In this work, we formulate a novel bi-shifting semantic auto-encoder to learn the semantic representations of the target instances and reinforce the generalization ability of the projection function. The encoder aims at mapping the visual features into the semantic space by leveraging the visual features of target instances and is guided by the semantic prototypes of seen classes. While two decoders manage to respectively reconstruct the original visual features in the source and target domains. Thus, our model can capture the generalized semantic characteristics related with the seen and unseen classes to alleviate the projection function problem. Furthermore, we develop an efficient algorithm by the advantage of the linear projection functions. Extensive experiments on the five benchmark datasets demonstrate the competitive performance of our proposed model.&lt;/p&gt;&lt;/abstract&gt;

Benchmarking Human Performance for Visual Search of Aerial Images.

Aerial images are frequently used in geospatial analysis to inform responses to crises and disasters but can pose unique challenges for visual search when they contain low resolution, degraded information about color, and small object sizes. Aerial image analysis is often performed by humans, but machine learning approaches are being developed to complement manual analysis. To date, however, relatively little work has explored how humans perform visual search on these tasks, and understanding this could ultimately help enable human-machine teaming. We designed a set of studies to understand what features of an aerial image make visual search difficult for humans and what strategies humans use when performing these tasks. Across two experiments, we tested human performance on a counting task with a series of aerial images and examined the influence of features such as target size, location, color, clarity, and number of targets on accuracy and search strategies. Both experiments presented trials consisting of an aerial satellite image; participants were asked to find all instances of a search template in the image. Target size was consistently a significant predictor of performance, influencing not only accuracy of selections but the order in which participants selected target instances in the trial. Experiment 2 demonstrated that the clarity of the target instance and the match between the color of the search template and the color of the target instance also predicted accuracy. Furthermore, color also predicted the order of selecting instances in the trial. These experiments establish not only a benchmark of typical human performance on visual search of aerial images but also identify several features that can influence the task difficulty level for humans. These results have implications for understanding human visual search on real-world tasks and when humans may benefit from automated approaches.

A Two-Way alignment approach for unsupervised multi-Source domain adaptation

Domain adaptation aims at transferring knowledge from labeled source domain to unlabeled target domain. Current advances primarily concern single source domain and neglect the setting of multiple source domains. Previous unsupervised multi-source domain adaptation (MDA) algorithms only consider domain-level alignment, while neglecting the category-level information among multiple domains and the instance variations inside each domain. This paper introduces a Two-Way alignment framework for MDA (TWMDA), which considers both domain-level and category-level alignments, and addresses the instance variations. We first align the target and multiple sources on the domain-level by an adversarial learning process. To circumvent the drawbacks of adversarial learning, we further reduce the domain gap on the category-level by minimizing the distance between the category prototypes and unlabeled target instances. To address the instance variations, we design an instance weighting strategy for diverse source instances. The effectiveness of TWMDA is demonstrated on three benchmark datasets for image classification.

A Novel Metric-Learning-Based Method for Multi-Instance Textureless Objects’ 6D Pose Estimation

6D pose estimation of objects is essential for intelligent manufacturing. Current methods mainly place emphasis on the single object’s pose estimation, which limit its use in real-world applications. In this paper, we propose a multi-instance framework of 6D pose estimation for textureless objects in an industrial environment. We use a two-stage pipeline for this purpose. In the detection stage, EfficientDet is used to detect target instances from the image. In the pose estimation stage, the cropped images are first interpolated into a fixed size, then fed into a pseudo-siamese graph matching network to calculate dense point correspondences. A modified circle loss is defined to measure the differences of positive and negative correspondences. Experiments on the antenna support demonstrate the effectiveness and advantages of our proposed method.

Fuzzy information decomposition incorporated and weighted Relief-F feature selection: When imbalanced data meet incompletion

Data classification is an important computer task in data analysis, which suffers seriously unknown features, imbalanced class, and incomplete data. However, despite their vital yet practical significance, few results have been made on such three distinct issues. To address this problem, we propose a novel feature selection method for the data subject to incomplete data and imbalanced class, namely, improved fuzzy information decomposition (IFID) incorporated and weighted Relief-F (WRelief-F) feature selection. The main idea of the proposed feature selection method is threefold. (1) The proposed IFID algorithm can deal with the imbalanced class and incomplete data at the same time. (2) In IFID, a new membership function is provided to reflect the influence of the observed data on the missing values appropriately. Based on this establishment, a more delicate information decomposition is adopted to make a better recovery than the traditional FID. (3) After using IFID, WRelief-F is put forward to take the relationship of the target instance to inter-class instances and the intra-class instances into consideration in a proper manner. Finally, experiments on the seven public data sets are utilized to show the effectiveness and universal applicability of the proposed feature selection algorithm.

Dual Encoder Attention U-net for Nuclei Segmentation.

Nuclei segmentation in whole slide images (WSIs) stained with Hematoxylin and Eosin (H&E) dye, is a key step in computational pathology which aims to automate the laborious process of manual counting and segmentation. Nuclei segmentation is a challenging problem that involves challenges such as touching nuclei resolution, small-sized nuclei, size, and shape variations. With the advent of deep learning, convolution neural networks (CNNs) have shown a powerful ability to extract effective representations from microscopic H&E images. We propose a novel dual encoder Attention U-net (DEAU) deep learning architecture and pseudo hard attention gating mechanism, to enhance the attention to target instances. We added a new secondary encoder to the attention U-net to capture the best attention for a given input. Since H captures nuclei information, we propose a stain-separated H channel as input to the secondary encoder. The role of the secondary encoder is to transform attention prior to different spatial resolutions while learning significant attention information. The proposed DEAU performance was evaluated on three publicly available H&E data sets for nuclei segmentation from different research groups. Experimental results show that our approach outperforms other attention-based approaches for nuclei segmentation.