Cross-domain Image Classification Research Articles

Study on Image Classification Algorithm Based on Multi-Scale Feature Fusion and Domain Adaptation

This paper introduces the MMTADAN, an innovative algorithm designed to enhance cross-domain image classification. By integrating multi-scale feature extraction with Taylor series-based detail enhancement and adversarial domain adaptation, the MMTADAN effectively aligns features between the source and target domains. The proposed approach addresses the critical challenge of generalizing classification models across diverse datasets, demonstrating significant improvements in performance. The findings suggest that retaining essential image details through multi-scale extraction and Taylor series enhancement can lead to better classification outcomes, making the MMTADAN a valuable contribution to the field of image classification.

Approximate geometric structure transfer for cross-domain image classification

The main purpose of domain adaptation (DA) is to conduct cross-domain related knowledge transfer. Considering the issue of unsupervised DA (UDA), learning a transformation that reduces the differences between domains is the primary goal. In addition to minimizing both the marginal and conditional distributions between the source and target domains, many methods explore potential factors that show the commonalities among domains to yield improved learning efficiency. However, geometric structure information is overlooked by most existing approaches, indicating that the shared information between domains has not been fully exploited. On account of this finding, by taking advantage of more potential shared factors to further enhance the results of DA, we propose an approximate geometric structure transfer (AGST) method for cross-domain image classification in this paper. By combining structural consistency and sample reweighting techniques, AGST encodes the geometric structure information taken from the samples in both domains, enabling it to easily obtain richer interdomain features and effectively facilitate knowledge transfer. Extensive experiments are conducted on several cross-domain data benchmarks. The experimental results indicate that our AGST method can outperform many state-of-the-art algorithms.

A two-layer regression network for robust and accurate domain adaptation

Naturally, classification models suffer from severe performance degradation when they are tested on datasets different from the ones used in training. Unsupervised domain adaptation helps to improve the generalizability of a pre-trained model by transferring knowledge from the labeled source domain (i.e., training dataset) to the unlabeled target domain (i.e., test dataset). The typical way of domain adaptation is to align the data distributions in embedding spaces between source and target domains. However, most existing works only enhance cross-domain consistency in the latent space disregarding the impact of source samples on the target classification task. Besides, discovering a subspace shared by two domains first and then training a transfer classifier separately hardly ensures that the obtained target features are suited for the classification model. To address these issues, in this work, we propose a two-layer regression network for domain adaptation (TRN-DA). TRN-DA learns class-wise domain invariant feature representations by jointly optimizing three tasks: supervised classification of source domain, unsupervised reconstruction of target domain, and alignment of cross-domain distributions. Furthermore, we introduce the concept of weight (importance) for source instances so that the resulting classifier can adapt well to the target domain. We formulate the domain adaptation problem as a unified optimization problem and solve it in an iterative way. Experimental results on different cross-domain image classification tasks demonstrate the encouraging performance of our TRN-DA compared to several recent state-of-the-art methods.

Cross-Domain Image Classification via Multimodal Augmentations and Bacterial Foraging Optimization

Identification of diseases from body scans requires design of pre-processing, filtering, segmentation, feature representation, classification & post-processing operations. Existing deep learning-based classification models use context-specific segmentation followed by convolutions or transformer-based classification techniques. However, the majority of these models do not perform correlative analysis between different disease types. This limitation restricts their scalability and applicability in clinical scenarios. To address these limitations, this research work proposed IMAC-MOC, a model that integrates multimodal augmentations to enhance performance in cross-domain and multi-organ image classification. The proposed model initially collects large-scale scans at organ-level like MRI, CT scan, Kidney Scans, etc. and represents them via multimodal feature sets. These feature maps are combined and processed via a Bacterial Foraging Optimizer (BFO) which assists in identification of high variance inter-class feature sets.

Source-Guided Target Feature Reconstruction for Cross-Domain Classification and Detection.

Existing cross-domain classification and detection methods usually apply a consistency constraint between the target sample and its self-augmentation for unsupervised learning without considering the essential source knowledge. In this paper, we propose a Source-guided Target Feature Reconstruction (STFR) module for cross-domain visual tasks, which applies source visual words to reconstruct the target features. Since the reconstructed target features contain the source knowledge, they can be treated as a bridge to connect the source and target domains. Therefore, using them for consistency learning can enhance the target representation and reduce the domain bias. Technically, source visual words are selected and updated according to the source feature distribution, and applied to reconstruct the given target feature via a weighted combination strategy. After that, consistency constraints are built between the reconstructed and original target features for domain alignment. Furthermore, STFR is connected with the optimal transportation algorithm theoretically, which explains the rationality of the proposed module. Extensive experiments on nine benchmarks and two cross-domain visual tasks prove the effectiveness of the proposed STFR module, e.g., 1) cross-domain image classification: obtaining average accuracy of 91.0%, 73.9%, and 87.4% on Office-31, Office-Home, and VisDA-2017, respectively; 2) cross-domain object detection: obtaining mAP of 44.50% on Cityscapes → Foggy Cityscapes, AP on car of 78.10% on Cityscapes → KITTI, MR -2 of 8.63%, 12.27%, 22.10%, and 40.58% on COCOPersons → Caltech, CityPersons → Caltech, COCOPersons → CityPersons, and Caltech → CityPersons, respectively.

Robust Label Propagation and Graph Embedding for Cross-Domain Image Classification

Robust Label Propagation and Graph Embedding for Cross-Domain Image Classification

Domain embedding transfer for unequal RGB-D image recognition

Most recent unsupervised domain adaptation (UDA) approaches concentrate on single RGB source to single RGB target task. They have to face the real-world scenario, where the source domain can be collected from multiple modalities, e.g., RGB data and depth data. Our work focuses on a more practical and challenging scenario which recognizes RGB images by learning from RGB-D data under the label inequality scenario. We are confronted with three challenges: multiple modalities in the source domain, domain shifting problem and unequal label numbers. To address the aforementioned settings, a novel method, referred to as Domain depth Embedding Transfer (DdET) is proposed, which takes advantage of the depth data in the source domain and handles the domain distribution mismatch under label inequality scenario simultaneously. We conduct comprehensive experiments on five cross domain image classification tasks and observe that DdET can perform favorably against state-of-the-art methods, especially under label inequality scenario.

Meta-transfer learning in cross-domain image classification with few-shot learning

Meta-transfer learning in cross-domain image classification with few-shot learning

Learning to Learn With Variational Inference for Cross-Domain Image Classification

Learning models that can generalize to previously unseen domains to which we have no access is a fundamental yet challenging problem in machine learning. In this paper, we propose meta variational inference (MetaVI), a variational Bayesian framework of meta-learning for cross domain image classification. Within the meta learning setting, MetaVI is derived to learn a probabilistic latent variable model by maximizing a meta evidence lower bound (Meta ELBO) for knowledge transfer across domains. To enhance the discriminative ability of the model, we further introduce a Wasserstein distance based constraint to the variational objective, leading to the Wasserstein MetaVI, which largely improves classification performance. By casting into a probabilistic inference problem, MetaVI offers the first, principled variational meta-learning framework for cross domain learning. In addition, we collect a new visual recognition dataset to contribute a more challenging benchmark for cross domain learning, which will be released to the public. Extensive experimental evaluation and ablation studies on four benchmarks show that our Wasserstein MetaVI achieves new state-of-the-art performance and surpasses previous methods, demonstrating its great effectiveness.

Guided Discrimination and Correlation Subspace Learning for Domain Adaptation.

As a branch of transfer learning, domain adaptation leverages useful knowledge from a source domain to a target domain for solving target tasks. Most of the existing domain adaptation methods focus on how to diminish the conditional distribution shift and learn invariant features between different domains. However, two important factors are overlooked by most existing methods: 1) the transferred features should be not only domain invariant but also discriminative and correlated, and 2) negative transfer should be avoided as much as possible for the target tasks. To fully consider these factors in domain adaptation, we propose a guided discrimination and correlation subspace learning (GDCSL) method for cross-domain image classification. GDCSL considers the domain-invariant, category-discriminative, and correlation learning of data. Specifically, GDCSL introduces the discriminative information associated with the source and target data by minimizing the intraclass scatter and maximizing the interclass distance. By designing a new correlation term, GDCSL extracts the most correlated features from the source and target domains for image classification. The global structure of the data can be preserved in GDCSL because the target samples are represented by the source samples. To avoid negative transfer issues, we use a sample reweighting method to detect target samples with different confidence levels. A semi-supervised extension of GDCSL (Semi-GDCSL) is also proposed, and a novel label selection scheme is introduced to ensure the correction of the target pseudo-labels. Comprehensive and extensive experiments are conducted on several cross-domain data benchmarks. The experimental results verify the effectiveness of the proposed methods over state-of-the-art domain adaptation methods.

A Novel Multi-Source Domain Adaptation Method with Dempster–Shafer Evidence Theory for Cross-Domain Classification

In this era of big data, Multi-source Domain Adaptation (MDA) becomes more and more popular and is employed to make full use of available source data collected from several different, but related domains. Although multiple source domains provide much information, the processing of domain shifts becomes more challenging, especially in learning a common domain-invariant representation for all domains. Moreover, it is counter-intuitive to treat multiple source domains equally as most existing MDA algorithms do. Therefore, the domain-specific distribution for each source–target domain pair is aligned, respectively. Nevertheless, it is hard to combine adaptation outputs from different domain-specific classifiers effectively, because of ambiguity on the category boundary. Subjective Logic (SL) is introduced to measure the uncertainty (credibility) of each domain-specific classifier, so that MDA could be bridged with DST. Due to the advantage of information fusion, Dempster–Shafer evidence Theory (DST) is utilized to reduce the category boundary ambiguity and output reasonable decisions by combining adaptation outputs based on uncertainty. Finally, extensive comparative experiments on three popular benchmark datasets for cross-domain image classification are conducted to evaluate the performance of the proposed method via various aspects.

Unsupervised domain adaptation based on adaptive local manifold learning

Transfer learning is known to an effective method dealing with domain shift. When the same task is shared in different domains, it is usually called domain adaptation. The problem of distribution difference is inevitable in domain adaption works. The subspace method can transform the data into a new feature representation, which is helpful to reduce the distribution differences. At present, many researchers have made extensive exploration on subspace learning in domain adaptation works. The weakness of many existed domain adaptation methods based on subspace learning either ignores the local manifold information or has the problem of parameter selection in local manifold regularization term which may limit the effectiveness of cross - domain image classification. Therefore, a novel transfer learning method termed unsupervised domain adaptation based on adaptive local manifold learning (UDA-ALML) is proposed in this paper, which is mainly utilized to cross-domain image classification. For the sake of preserving the structure information of original data, the proposed method combines sparse representation, manifold learning and low rank representation to learn the transformation matrix. To be specific, the weight matrix in traditional local manifold regularization term is replaced by the reconstruction coefficient matrix. Large quantities of experiments show that it has a remarkable performance in cross-domain image recognition.

Attention Regularized Laplace Graph for Domain Adaptation.

In leveraging manifold learning in domain adaptation (DA), graph embedding-based DA methods have shown their effectiveness in preserving data manifold through the Laplace graph. However, current graph embedding DA methods suffer from two issues: 1). they are only concerned with preservation of the underlying data structures in the embedding and ignore sub-domain adaptation, which requires taking into account intra-class similarity and inter-class dissimilarity, thereby leading to negative transfer; 2). manifold learning is proposed across different feature/label spaces separately, thereby hindering unified comprehensive manifold learning. In this paper, starting from our previous DGA-DA, we propose a novel DA method, namely A ttention R egularized Laplace G raph-based D omain A daptation (ARG-DA), to remedy the aforementioned issues. Specifically, by weighting the importance across different sub-domain adaptation tasks, we propose the A ttention R egularized Laplace Graph for class aware DA, thereby generating the attention regularized DA. Furthermore, using a specifically designed FEEL strategy, our approach dynamically unifies alignment of the manifold structures across different feature/label spaces, thus leading to comprehensive manifold learning. Comprehensive experiments are carried out to verify the effectiveness of the proposed DA method, which consistently outperforms the state of the art DA methods on 7 standard DA benchmarks, i.e., 37 cross-domain image classification tasks including object, face, and digit images. An in-depth analysis of the proposed DA method is also discussed, including sensitivity, convergence, and robustness.

Deep Transfer Learning for Biology Cross-Domain Image Classification

Automatic biology image classification is essential for biodiversity conservation and ecological study. Recently, due to the record-shattering performance, deep convolutional neural networks (DCNNs) have been used more often in biology image classification. However, training DCNNs requires a large amount of labeled data, which may be difficult to collect for some organisms. This study was carried out to exploit cross-domain transfer learning for DCNNs with limited data. According to the literature, previous studies mainly focus on transferring from ImageNet to a specific domain or transferring between two closely related domains. While this study explores deep transfer learning between species from different domains and analyzes the situation when there is a huge difference between the source domain and the target domain. Inspired by the analysis of previous studies, the effect of biology cross-domain image classification in transfer learning is proposed. In this work, the multiple transfer learning scheme is designed to exploit deep transfer learning on several biology image datasets from different domains. There may be a huge difference between the source domain and the target domain, causing poor performance on transfer learning. To address this problem, multistage transfer learning is proposed by introducing an intermediate domain. The experimental results show the effectiveness of cross-domain transfer learning and the importance of data amount and validate the potential of multistage transfer learning.

A self-supervised feature-standardization-block for cross-domain lung disease classification.

With the advance of deep learning technology, convolutional neural network (CNN) has been wildly used and achieved the state-of-the-art performances in the area of medical image classification. However, most existing medical image classification methods conduct their experiments on only one public dataset. When applying a well-trained model to a different dataset selected from different sources, the model usually shows large performance degradation and needs to be fine-tuned before it can be applied to the new dataset. The goal of this work is trying to solve the cross-domain image classification problem without using data from target domain. In this work, we designed a self-supervised plug-and-play feature-standardization-block (FSB) which consisting of image normalization (INB), contrast enhancement (CEB) and boundary detection blocks (BDB), to extract cross-domain robust feature maps for deep learning framework, and applied the network for chest x-ray-based lung diseases classification. Three classic deep networks, i.e. VGG, Xception and DenseNet and four chest x-ray lung diseases datasets were employed for evaluating the performance. The experimental result showed that when employing feature-standardization-block, all three networks showed better domain adaption performance. The image normalization, contrast enhancement and boundary detection blocks achieved in average 2%, 2% and 5% accuracy improvement, respectively. By combining all three blocks, feature-standardization-block achieved in average 6% accuracy improvement.

Domain adaptation with geometrical preservation and distribution alignment

Domain adaptation aims to learn a robust classifier for the target domain by leveraging knowledge from a different source domain. Existing methods realize the alignment of cross-domain distributions in manifold subspace to reduce the distribution divergence between the two domains. However, there exists a conspicuous deficiency in them, i.e., the exploration of preserving statistical and geometrical properties simultaneously is still under insufficient, which, to some extent, would cause the under adaptation effect. The statistical and geometrical properties play an important role in minimizing the domain discrepancy underlying the joint probability distributions. For better and adequately exploiting the statistical and geometrical properties, we propose a novel feature adaptation method in this paper, called domain adaptation with geometrical preservation and distribution alignment (GPDA). Specifically, GPDA performs graph dual regularization in the nonnegative matrix factorization framework with label constraints, to learn the discriminative and domain-invariant features while preserving both the statistical properties and geometrical structures of the original data, such that the cross-domain difference can be effectively and positively narrowed. Meanwhile, GPDA simultaneously aligns the marginal and conditional probability distributions in the nonnegative matrix factorization framework during the learning of domain-invariant features, to further minimize the domain gap between the source and target domains, which can adequately transfer knowledge from the source domain to the target domain. Extensive experiments on seven benchmark datasets demonstrate the effectiveness of the proposed GPDA algorithm in cross-domain image classification.

Joint Adaptive Dual Graph and Feature Selection for Domain Adaptation

Domain adaptation aims to exploit domain-invariant features by aligning the cross-domain distributions in the manifold subspace for applying the classifier trained on the source domain to the target domain. However, two limitations may still deteriorate their performances: (1) the influences of noisy or irrelevant features in the original feature space are ignored, which may unexpectedly hurt the classification of target samples; (2) the graph constructed directly in the original data space cannot accurately capture the inherent local manifold structures of high-dimensional data due to the curse of dimensionality, which may seriously mislead the transferable features learning. In this paper, we propose a novel approach to address these problems, referred to as joint Adaptive Dual Graph and Feature Selection for domain adaptation (ADGFS). Specifically, feature selection can characterize the relative importance of different features through a scaling factor, which enables ADGFS to not only reduce the impacts of noisy or irrelevant features on knowledge transfer but also learn informative domain-invariant features. Meanwhile, ADGFS adaptively optimizes the dual graph by learning the similarity matrices of both instance-level and feature-level graphs in the projected low-dimensional manifold subspace rather than the original high-dimensional space, such that the intrinsic local manifold structures of data can be captured precisely. Moreover, ADGFS simultaneously aligns the marginal and conditional probability distributions in the nonnegative matrix factorization framework to narrow the distribution discrepancies between the two different domains, which can adequately transfer knowledge from the source domain to the target domain. Comprehensive experiments on four benchmark datasets can demonstrate that the effectiveness of the proposed approach in cross-domain image classification.

Discriminative Transfer Feature and Label Consistency for Cross-Domain Image Classification.

Visual domain adaptation aims to seek an effective transferable model for unlabeled target images by benefiting from the well-labeled source images following different distributions. Many recent efforts focus on extracting domain-invariant image representations via exploring target pseudo labels, predicted by the source classifier, to further mitigate the conditional distribution shift across domains. However, two essential factors are overlooked by most existing methods: 1) the learned transferable features should be not only domain invariant but also category discriminative; and 2) the target pseudo label is a two-edged sword to cross-domain alignment. In other words, the wrongly predicted target labels may hinder the class-wise domain matching. In this article, to address these two issues simultaneously, we propose a discriminative transfer feature and label consistency (DTLC) approach for visual domain adaptation problems, which can naturally unify cross-domain alignment with discriminative information preserved and label consistency of source and target data into one framework. To be specific, DTLC first incorporates class discriminative information by penalizing the maximum distance of data pair in the same class and the minimum distance of data pair sharing the different labels for each data into the distribution alignment of both domains. The target pseudo labels are then refined based on the label consistency within the domains. Thus, the transfer feature learning and coarse-to-fine target labels would be coupled to benefit each other in an iterative way. Comprehensive experiments on several visual cross-domain benchmarks verify that DTLC can gain remarkable margins over state-of-the-art (SOTA) nondeep visual domain adaptation methods and even be comparable to competitive deep domain adaptation ones.

DART: Domain-Adversarial Residual-Transfer networks for unsupervised cross-domain image classification

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled data but gains access to cheaply available unlabeled data, unsupervised domain adaptation is a promising technique to boost the performance without incurring extra labeling cost, by assuming images from different domains share some invariant characteristics. In this paper, we propose a new unsupervised domain adaptation method named Domain-Adversarial Residual-Transfer (DART) learning of deep neural networks to tackle cross-domain image classification tasks. In contrast to the existing unsupervised domain adaption approaches, the proposed DART not only learns domain-invariant features via adversarial training, but also achieves robust domain-adaptive classification via a residual-transfer strategy, all in an end-to-end training framework. We evaluate the performance of the proposed method for cross-domain image classification tasks on several well-known benchmark data sets, in which our method clearly outperforms the state-of-the-art approaches.

Enhancing unsupervised domain adaptation by discriminative relevance regularization

Unsupervised domain adaptation (UDA) serves to transfer specific knowledge from massive labeled source domain data to unlabeled target domain data via mitigating domain shift. In this paper, we propose a discriminative relevance regularization term (DRR) to enhance the performance of UDA by reducing the domain shift from the aspect of semantic relevance across domains. In particular, DRR is formulated as the min–max rank problem which seeks a projection matrix to minimize the rank of intra-class projected features and maximize the rank of the means of inter-class projected features simultaneously. To test the potential effectiveness of DRR, we design a relevance regularized distribution adaptation method (RRDA) and relevance regularized adaptation networks (RRAN) for image classification, and a relevance regularized self-supervised learning method (RRSL) for semantic segmentation by incorporation of DRR. The corresponding optimization algorithms are proposed to solve them. Experiments of cross-domain image classification show that both RRDA and RRAN outperform several state-of-the-art compared methods. Moreover, experiments of domain-adaptation semantic segmentation on two synthetic-to-real segmentation datasets demonstrate the capacity of RRSL. Such results imply the efficacy of DRR on both image classification and semantic segmentation tasks.