Transductive Approach Research Articles

Chinese text classification by combining Chinese-BERTology-wwm and GCN.

Text classification is an important and classic application in natural language processing (NLP). Recent studies have shown that graph neural networks (GNNs) are effective in tasks with rich structural relationships and serve as effective transductive learning approaches. Text representation learning methods based on large-scale pretraining can learn implicit but rich semantic information from text. However, few studies have comprehensively utilized the contextual semantic and structural information for Chinese text classification. Moreover, the existing GNN methods for text classification did not consider the applicability of their graph construction methods to long or short texts. In this work, we propose Chinese-BERTology-wwm-GCN, a framework that combines Chinese bidirectional encoder representations from transformers (BERT) series models with whole word masking (Chinese-BERTology-wwm) and the graph convolutional network (GCN) for Chinese text classification. When building text graph, we use documents and words as nodes to construct a heterogeneous graph for the entire corpus. Specifically, we use the term frequency-inverse document frequency (TF-IDF) to construct the word-document edge weights. For long text corpora, we propose an improved pointwise mutual information (PMI*) measure for words according to their word co-occurrence distances to represent the weights of word-word edges. For short text corpora, the co-occurrence information between words is often limited. Therefore, we utilize cosine similarity to represent the word-word edge weights. During the training stage, we effectively combine the cross-entropy and hinge losses and use them to jointly train Chinese-BERTology-wwm and GCN. Experiments show that our proposed framework significantly outperforms the baselines on three Chinese benchmark datasets and achieves good performance even with few labeled training sets.

Open set text recognition technology

开放环境下的模式识别与文字识别应用中，新数据、新模式和新类别不断涌现，要求算法具备应对新类别模式的能力。针对这一问题，研究者们开始聚焦开放集文字识别（open-set text recognition，OSTR）任务。该任务要求，算法在测试（推断）阶段，既能识别训练集见过的文字类别，还能够识别、拒识或发现训练集未见过的新文字。开放集文字识别逐步成为文字识别领域的研究热点之一。本文首先对开放集模式识别技术进行简要总结，然后重点介绍开放集文字识别的研究背景、任务定义、基本概念、研究重点和技术难点。同时，针对开放集文字识别三大问题（未知样本发现、新类别识别和上下文信息偏差），从方法的模型结构、特点优势和应用场景的角度对相关工作进行了综述。最后，对开放集文字识别技术的发展趋势和研究方向进行了分析展望。;Text recognition is focused on text transcription-based image processing modeling in relevance to such domains like document digitization, content moderation, scene text translation, automation driving, scene understanding, and other related contexts. Conventional text recognition techniques are often concerned about characters-seen recognition more. However, two factors in the training set of these methods are yet to be well covered, which are novel character categories and out-of-vocabulary (OOV) samples. Newly characters-related samples are often linked with OOV-based samples. However, it may pay attention to seen characters without novel combinations or contexts. For novel character categories, internet-based environments can be mainly used to face unseen ligatures like 1) emoticons and unperceived languages, 2) scene-text recognition environments, and 3) characters from foreign and region-specific languages. For digitization profiling, the undiscovered characters may not be involved in as well. Since the heterogeneity of language format to be balanced, the linguistic statistic data(e. g., n-gram, context, etc.) can be biased the training data gradually, which is challenged for vocabulary-high-correlated text recognition methods. The two factors are required to yield three key scientific problems that affect the costs or efficiency in open-world applications. The novel characters are oriented for the novel spotting capability, whereas characters-unseen are rejected to replace silent seen characters. Furthermore, as the popular open-set recognition problem, three scientific problems can be leaked out as mentioned below. First, the emergence of novel characters is not efficient in many cases, in which re-training upon each occurrence is costly, and an incremental learning capability need to be strengthened after that. Second, an amount of attention is received as the generalized zeroshot learning text recognition task. Third, Linguistic bias robustness is yielded by the OOV samples. Due to the characterbased nature prediction, more popular methods can be used to possess the capability to handle characters-seen OOV samples to some extent. However, such capabilities are constrained to demonstrate strong vocabulary reliance because of the capacity of language models, the open-set text recognition(OSTR) task is feasible since existing tasks like zero-shot text recognition and OOV recognition can be used to model individual aspects of the problems only. This task aims to spot and recognize the novel characters, which is robust to linguistic skews. As an extension of the conventional text recognition task, the OSTR task is used to retain a decent recognition capability on seen contents. In recent years, the OSTR task has been developing intensively in the context of character recognition. The literature review is carried out on the open-set text recognition task and its related domains. It consists of such five aspects of the background, genericity, the concept, implementation, and summary. For the background, we introduce the application background of the OSTR task and analyze the specific OSTR-derived cases. For genericity, the generic open-set recognition is introduced in brief as a preliminary of the OSTR task that is less familiar to some researchers in the text recognition field. For concept, the definition of the OSTR task is introduced, followed by a discussion on its relationship with existing text recognition tasks, e. g., conventional close-set text recognition task and the zero-shot text recognition task. Its implementation-wise, common text recognition frameworks are first introduced. For implementation, it can be recognized as derivations of such frameworks, where the derivation is based on the three key scientific problems as following:new category spotting, incremental recognition of novel classes, and linguistic bias robustness. Specifically, the new category spotting problem refers to rejecting samples that come from an absent class of a given label set. Slightly different from the generic open-set text recognition task, the given label-set is challenged in related to the training data straightfoward. Incremental recognition refers to new categories recognition in terms of the non-retrained side information of the corresponding categories. The definition is slightly different from the common zero-shot learning definition, it can be excluded some generative adversarial network(GAN)-based transductive approaches. The linguistic bias robustness holds its original definition beyond more stressed unseen characters. For each scientific problem, its solution can be covered in text recognition and other modeling-similar related fields. The evaluation is carried out and it can mainly cover the datasets and protocols used in the OSTR task and its contexts as listed:1) multiple protocols based public available datasets, 2) commonly used metric to measure model performance, and 3) several of popular protocols, typical methods, and the performance. Here, a protocol refers to the compositions of training sets, testing sets, and evaluation metrics. For summary, the comparative analysis of the growth and technical preference are demonstrated. Finally, the potnetialss of the trends and future research directions are predicted further.

Improving Neural Machine Translation for Low Resource Algerian Dialect by Transductive Transfer Learning Strategy.

This study is the first work on a transductive transfer learning approach for low-resource neural machine translation applied to the Algerian Arabic dialect. The transductive approach is based on a fine-tuning transfer learning strategy that transfers knowledge from the parent model to the child model. This strategy helps to solve the learning problem using limited parallel corpora. We tested the approach on a sequence-to-sequence model with and without the Attention mechanism. We first trained the models on a parallel multi-dialects Arabic corpus and then switch them to a low-resource of the Algerian dialect. Transductive transfer learning raises the BLEU score for the Seq2Seq model from 0.3 to more than 34, and for the Attentional-Seq2Seq model from less than 17 to more than 35. The obtained results prove the validity of this approach.

Encoding Post-Spectral Sound

This article examines computer-based music (ca. 1982–87) created by Finnish composer Kaija Saariaho at the Institut de Recherche et Coordination Acoustique/Musique (IRCAM) in Paris. A detailed account of archival materials for an early étude in voice synthesis,Vers le blanc(1982), demonstrates the music-theoretical import of software to Saariaho’s development of a robust compositional method that resonated with the emergent aesthetics of a post-spectral milieu. Subsequent analyses of two additional works from this period—Jardin secret II(1984–86) for harpsichord and tape, andIO(1987) for large ensemble and electronics—serve to illustrate Saariaho’s extension of this method into instrumental settings. Specific techniques highlighted include the use of interpolation systems to create continuous processes of transformation, the organization of individual musical parameters into multidimensional formal networks, and the exploration of harmonic structures based on the analysis of timbral phenomena. Relating these techniques to the affordances of contemporaneous IRCAM technologies, including CHANT, FORMES, and Saariaho’s own customized program, “transkaija,” this article adopts a transductive approach to archival research that is responsive to the diverse media artifacts associated with computer-based composition.

Transductive Transfer Learning for Domain Adaptation in Brain Magnetic Resonance Image Segmentation.

Segmentation of brain images from Magnetic Resonance Images (MRI) is an indispensable step in clinical practice. Morphological changes of sub-cortical brain structures and quantification of brain lesions are considered biomarkers of neurological and neurodegenerative disorders and used for diagnosis, treatment planning, and monitoring disease progression. In recent years, deep learning methods showed an outstanding performance in medical image segmentation. However, these methods suffer from generalisability problem due to inter-centre and inter-scanner variabilities of the MRI images. The main objective of the study is to develop an automated deep learning segmentation approach that is accurate and robust to the variabilities in scanner and acquisition protocols. In this paper, we propose a transductive transfer learning approach for domain adaptation to reduce the domain-shift effect in brain MRI segmentation. The transductive scenario assumes that there are sets of images from two different domains: (1) source—images with manually annotated labels; and (2) target—images without expert annotations. Then, the network is jointly optimised integrating both source and target images into the transductive training process to segment the regions of interest and to minimise the domain-shift effect. We proposed to use a histogram loss in the feature level to carry out the latter optimisation problem. In order to demonstrate the benefit of the proposed approach, the method has been tested in two different brain MRI image segmentation problems using multi-centre and multi-scanner databases for: (1) sub-cortical brain structure segmentation; and (2) white matter hyperintensities segmentation. The experiments showed that the segmentation performance of a pre-trained model could be significantly improved by up to 10%. For the first segmentation problem it was possible to achieve a maximum improvement from 0.680 to 0.799 in average Dice Similarity Coefficient (DSC) metric and for the second problem the average DSC improved from 0.504 to 0.602. Moreover, the improvements after domain adaptation were on par or showed better performance compared to the commonly used traditional unsupervised segmentation methods (FIRST and LST), also achieving faster execution time. Taking this into account, this work presents one more step toward the practical implementation of deep learning algorithms into the clinical routine.

A transductive transfer learning approach for image classification

Among machine learning paradigms, unsupervised transductive transfer learning is useful when no labeled data from the target domain are available at training time, but there is accessible unlabeled target data during training phase instead. The current paper proposes a novel unsupervised transductive transfer learning method to find the specific and shared features across the source and the target domains. The proposed learning method then maps both domains into the respective subspaces with minimum marginal and conditional distribution divergences. It is shown that the discriminative learning across domains leads to boost the model performance. Hence, the proposed method discriminates the classes of both domains via maximizing the distance between each sample-pairs with different labels and via minimizing the distance between each instance-pairs of the same classes. We verified our approach using standard visual benchmarks, with the average accuracy of 46 experiments as 76.5%, which rates rather high in comparison with other state-of-the-art transfer learning methods through various cross-domain tasks.

Semi-Supervised Cyber Threat Identification in Dark Net Markets: A Transductive and Deep Learning Approach

ABSTRACT Dark Net Marketplaces (DNMs), online selling platforms on the dark web, constitute a major component of the underground economy. Due to the anonymity and increasing accessibility of these platforms, they are rich sources of cyber threats such as hacking tools, data breaches, and personal account information. As the number of products offered on DNMs increases, researchers have begun to develop automated machine learning-based threat identification approaches. A major challenge in adopting such an approach is that the task typically requires manually labeled training data, which is expensive and impractical. We propose a novel semi-supervised labeling technique for leveraging unlabeled data based on the lexical and structural characteristics of DNMs using transductive learning. Empirical results show that the proposed approach leads to an approximately 3-5% increase in classification performance measured by F1-score, while increasing both precision and recall. To further improve the identification performance, we adopt Long Short-Term Memory (LSTM) as a deep learning structure on top of the proposed labeling method. The results are evaluated against a large collection of 79K product listings obtained from the most popular DNMs. Our method outperforms the state-of-the-art methods in threat identification and is considered as an important step toward lowering the human supervision cost in realizing automated threat detection within cyber threat intelligence organizations.

Anomaly and Novelty detection for robust semi-supervised learning

Three important issues are often encountered in Supervised and Semi-Supervised Classification: class-memberships are unreliable for some training units (label noise), a proportion of observations might depart from the main structure of the data (outliers) and new groups in the test set may have not been encountered earlier in the learning phase (unobserved classes). The present work introduces a robust and adaptive Discriminant Analysis rule, capable of handling situations in which one or more of the afore-mentioned problems occur. Two EM-based classifiers are proposed: the first one that jointly exploits the training and test sets (transductive approach), and the second one that expands the parameter estimate using the test set, to complete the group structure learned from the training set (inductive approach). Experiments on synthetic and real data, artificially adulterated, are provided to underline the benefits of the proposed method.

Multi-source domain adaptation for image classification

In recent years, domain adaptation and transfer learning are known as promising techniques with admirable performance to deal with problems with distribution difference between the training (source domain) and test (target domain) data. In this paper, a novel unsupervised multi-source transductive transfer learning approach, referred to as multi-source domain adaptation for image classification (MDA), is proposed, to transfer knowledge across the selected samples of multiple-source domains and samples of target domain into a shared low-dimensional subspace with maximum decision regions. MDA extends maximum mean discrepancy criteria across multiple-source domains to find an optimal projection subspace and constructs embedded condensed domain-invariant clusters. Furthermore, MDA minimizes empirical risk and maximizes the rate of consistency between manifold and prediction function via learning an optimal classification. Extensive evaluations on two types of visual benchmark datasets under different difficulties illustrate that MDA significantly outperforms other baseline and state-of-the-art methods in both multiple- and single-source tasks. Our source code is available at https://github.com/jtahmores/MDA .

Structure alignment of attributes and visual features for cross-dataset person re-identification

In cross-dataset person re-identification, it is challenging to address the problem of domain shift between training and test data. Although unsupervised domain adaptation methods have been developed, the performance is still much weaker compared with that of supervised methods because these models cannot follow a supervised optimization in unlabeled target domains. To address this problem, a transductive structure alignment-based self-reconstruction dictionary learning approach is proposed in this paper for cross-dataset person re-identification (PRID). Specifically, visual-attribute embedding is first learned to achieve knowledge transfer from the source domain to the target domain. In this process, visual-attribute structures are aligned via class prototype dictionaries to promote the discrimination of predicted semantic attributes by exploiting structure information between the visual feature and class prototype. Moreover, to mitigate domain shift, domain-invariant visual-attribute self-reconstruction is integrated into our dictionary learning framework. An identifier is then constructed by integrating the discriminativeness of attribute and compatibility matrix shared both source domain and target domain. Finally, the pre-learned model is tuned by selecting samples from the target domain which are not labeled but assigned pseudo-labels. Extensive experimental results on benchmark datasets show that our approach outperforms several state-of-the-art approaches.

Thumbs up, thumbs down: non-verbal human-robot interaction through real-time EMG classification via inductive and supervised transductive transfer learning

In this study, we present a transfer learning method for gesture classification via an inductive and supervised transductive approach with an electromyographic dataset gathered via the Myo armband. A ternary gesture classification problem is presented by states of ’thumbs up’, ’thumbs down’, and ’relax’ in order to communicate in the affirmative or negative in a non-verbal fashion to a machine. Of the nine statistical learning paradigms benchmarked over 10-fold cross validation (with three methods of feature selection), an ensemble of Random Forest and Support Vector Machine through voting achieves the best score of 91.74% with a rule-based feature selection method. When new subjects are considered, this machine learning approach fails to generalise new data, and thus the processes of Inductive and Supervised Transductive Transfer Learning are introduced with a short calibration exercise (15 s). Failure of generalisation shows that 5 s of data per-class is the strongest for classification (versus one through seven seconds) with only an accuracy of 55%, but when a short 5 s per class calibration task is introduced via the suggested transfer method, a Random Forest can then classify unseen data from the calibrated subject at an accuracy of around 97%, outperforming the 83% accuracy boasted by the proprietary Myo system. Finally, a preliminary application is presented through social interaction with a humanoid Pepper robot, where the use of our approach and a most-common-class metaclassifier achieves 100% accuracy for all trials of a ‘20 Questions’ game.

A Transductive Transfer Learning Approach Based on Manifold Learning

Traditional machine learning approaches usually assume that the training data and the test data follow the same distribution. When the training data and the test data are not drawn from the same distribution, most traditional machine learning approaches cannot work well. Transfer learning approaches allow the distributions of the training data and the test data to be different. Transfer learning approaches mainly focus on how to reduce the difference between the training data and the test data, but mostly ignore the potential semantic information. This paper proposes a transductive transfer learning approach based on manifold learning (TTL-ML). TTL-ML designs a new feature representation space, where the semantic information hidden in the dataset structure is preserved, and the distribution difference between the source domain and the target domain is reduced. Experimental results on the common transfer learning datasets demonstrate that the proposed approach outperforms the several state-of-the-art approaches on image classification.

Deep Ranking for Image Zero-Shot Multi-Label Classification.

During the past decade, both multi-label learning and zero-shot learning have attracted huge research attention, and significant progress has been made. Multi-label learning algorithms aim to predict multiple labels given one instance, while most existing zero-shot learning approaches target at predicting a single testing label for each unseen class via transferring knowledge from auxiliary seen classes to target unseen classes. However, relatively less effort has been made on predicting multiple labels in the zero-shot setting, which is nevertheless a quite challenging task. In this work, we investigate and formalize a flexible framework consisting of two components, i.e., visual-semantic embedding and zero-shot multi-label prediction. First, we present a deep regression model to project the visual features into the semantic space, which explicitly exploits the correlations in the intermediate semantic layer of word vectors and makes label prediction possible. Then, we formulate the label prediction problem as a pairwise one and employ Ranking SVM to seek the unique multi-label correlations in the embedding space. Furthermore, we provide a transductive multi-label zeroshot prediction approach that exploits the testing data manifold structure. We demonstrate the effectiveness of the proposed approach on three popular multi-label datasets with state-of-theart performance obtained on both conventional and generalized ZSL settings.

Learning Unbiased Zero-Shot Semantic Segmentation Networks Via Transductive Transfer

Semantic segmentation aims to obtain a detailed understanding of images. Deep learning has achieved great advances in semantic segmentation over the past years. In practice, however, the classes do not always correspond to the ones in the training stage. Since it is impractical to collect sufficient labeled data for all classes, zero-shot semantic segmentation has received increasing attentions recently. Although semantic segmentation neural networks can transfer knowledge from seen classes to unseen classes by incorporating the class-level semantic information, it shows a strong bias towards seen classes. In this letter, we propose an easy-to-implement transductive approach to alleviate the prediction bias in zero-shot semantic segmentation. We assume that both source images with full pixel-level labels and unlabeled target images are available for training. The source images are used to build the relationship between visual images and class-level semantic embeddings. On the other hand, the target images are used to alleviate the bias towards seen classes. Comprehensive experiments over the PASCAL dataset clearly demonstrate the effectiveness of our approach.

Discovery and annotation of novel microRNAs in the porcine genome by using a semi-supervised transductive learning approach

Despite the broad variety of available microRNA (miRNA) prediction tools, their application to the discovery and annotation of novel miRNA genes in domestic species is still limited. In this study we designed a comprehensive pipeline (eMIRNA) for miRNA identification in the yet poorly annotated porcine genome and demonstrated the usefulness of implementing a motif search positional refinement strategy for the accurate determination of precursor miRNA boundaries. The small RNA fraction from gluteus medius skeletal muscle of 48 Duroc gilts was sequenced and used for the prediction of novel miRNA loci. Additionally, we selected the human miRNA annotation for a homology-based search of porcine miRNAs with orthologous genes in the human genome. A total of 20 novel expressed miRNAs were identified in the porcine muscle transcriptome and 27 additional novel porcine miRNAs were also detected by homology-based search using the human miRNA annotation. The existence of three selected novel miRNAs (ssc-miR-483, ssc-miR484 and ssc-miR-200a) was further confirmed by reverse transcription quantitative real-time PCR analyses in the muscle and liver tissues of Göttingen minipigs. In summary, the eMIRNA pipeline presented in the current work allowed us to expand the catalogue of porcine miRNAs and showed better performance than other commonly used miRNA prediction approaches. More importantly, the flexibility of our pipeline makes possible its application in other yet poorly annotated non-model species.

Data mining and machine learning approaches for prediction modelling of schistosomiasis disease vectors: Epidemic disease prediction modelling.

This research presents viable solutions for prediction modelling of schistosomiasis disease based on vector density. Novel training models proposed in this work aim to address various aspects of interest in the artificial intelligence applications domain. Topics discussed include data imputation, semi-supervised labelling and synthetic instance simulation when using sparse training data. Innovative semi-supervised ensemble learning paradigms are proposed focusing on labelling threshold selection and stringency of classification confidence levels. A regression-correlation combination (RCC) data imputation method is also introduced for handling of partially complete training data. Results presented in this work show data imputation precision improvement over benchmark value replacement using proposed RCC on 70% of test cases. Proposed novel incremental transductive models such as ITSVM have provided interesting findings based on threshold constraints outperforming standard SVM application on 21% of test cases and can be applied with alternative environment-based epidemic disease domains. The proposed incremental transductive ensemble approach model enables the combination of complimentary algorithms to provide labelling for unlabelled vector density instances. Liberal (LTA) and strict training approaches provided varied results with LTA outperforming Stacking ensemble on 29.1% of test cases. Proposed novel synthetic minority over-sampling technique (SMOTE) equilibrium approach has yielded subtle classification performance increases which can be further interrogated to assess classification performance and efficiency relationships with synthetic instance generation.

Machine Learning Approach for Identification of Microstructure–Process Linkages

The present work addresses a machine learning approach to study the linkage between deformation processing and microstructural texture evolution. The texture evolution is represented with a one-point probability descriptor, orientation distribution function (ODF) by employing a rate-independent single-crystal plasticity model. The ODF relates to the volume densities of different orientations in a microstructure, and thus it quantifies the texture during processing. First, a database of microstructural textures and deformation processes is built to generate the training dataset. The Latin hypercube sampling method is implemented to create uniformly distributed ODF values that represent the initial texture. Next, the crystal plasticity simulations using the initial ODF samples are performed for different deformation processes such as tension, plane strain compression, shear, shear, and shear; and the final texture information is stored in the database. Transductive learning is employed by using the training data to predict the label (optimum process) that can produce a given unlabeled texture. Two example process design applications are discussed for a galfenol alloy. In the first problem, the transductive learning approach is verified by using the previously optimized ODF solutions for a vibration tuning problem. In the second example, the process design is performed for a multiphysics optimization problem.

Cross-domain aspect extraction for sentiment analysis: A transductive learning approach

Aspect-Based Sentiment Analysis (ABSA) is a promising approach to analyze consumer reviews at a high level of detail, where the opinion about each feature of the product or service is considered. ABSA usually explores supervised inductive learning algorithms, which requires intense human effort for the labeling process. In this paper, we investigate Cross-Domain Transfer Learning approaches, in which aspects already labeled in some domains can be used to support the aspect extraction of another domain where there are no labeled aspects. Existing cross-domain transfer learning approaches learn classifiers from labeled aspects in the source domain and then apply these classifiers in the target domain, i.e., two separate stages that may cause inconsistency due to different feature spaces. To overcome this drawback, we present an innovative approach called CD-ALPHN (Cross-Domain Aspect Label Propagation through Heterogeneous Networks). First, we propose a heterogeneous network-based representation that combines different features (labeled aspects, unlabeled aspects, and linguistic features) from source and target domain as nodes in a single network. Second, we propose a label propagation algorithm for aspect extraction from heterogeneous networks, where the linguistic features are used as a bridge for this propagation. Our algorithm is based on a transductive learning process, where we explore both labeled and unlabeled aspects during the label propagation. Experimental results show that the CD-ALPHN outperforms the state-of-the-art methods in scenarios where there is a high-level of inconsistency between the source and target domains — the most common scenario in real-world applications.

Representation Learning for Classification in Heterogeneous Graphs with Application to Social Networks

We address the task of node classification in heterogeneous networks, where the nodes are of different types, each type having its own set of labels, and the relations between nodes may also be of different types. A typical example is provided by social networks where node types may for example be users, content, or films, and relations friendship , like , authorship . Learning and performing inference on such heterogeneous networks is a recent task requiring new models and algorithms. We propose a model, Labeling Heterogeneous Network (LaHNet) , a transductive approach to classification that learns to project the different types of nodes into a common latent space. This embedding is learned so as to reflect different characteristics of the problem such as the correlation between node labels, as well as the graph topology. The application focus is on social graphs, but the algorithm is general and can be used for other domains. The model is evaluated on five datasets representative of different instances of social data.

Transductive Zero-Shot Learning With a Self-Training Dictionary Approach.

As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data. To address this problem, ZSL is usually carried out in the following two aspects: 1) capturing the domain distribution connections between seen classes data and unseen classes data and 2) modeling the semantic interactions between the image feature space and the label embedding space. Motivated by these observations, we propose a bidirectional mapping-based semantic relationship modeling scheme that seeks for cross-modal knowledge transfer by simultaneously projecting the image features and label embeddings into a common latent space. Namely, we have a bidirectional connection relationship that takes place from the image feature space to the latent space as well as from the label embedding space to the latent space. To deal with the domain shift problem, we further present a transductive learning approach that formulates the class prediction problem in an iterative refining process, where the object classification capacity is progressively reinforced through bootstrapping-based model updating over highly reliable instances. Experimental results on four benchmark datasets (animal with attribute, Caltech-UCSD Bird2011, aPascal-aYahoo, and SUN) demonstrate the effectiveness of the proposed approach against the state-of-the-art approaches.