Statistical and Geometrical Alignment using Metric Learning in Domain Adaptation

Sanodiya, Rakesh Kumar; Mathew, Alwyn; Mathew, Jimson; Khushi, Matloob

doi:10.1109/ijcnn48605.2020.9206877

Cited by 5 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the efficiency of our VTL, the results of our experiments are compared with several unsupervised domain adaptation methods including EMFS (2018) [40], EasyTL (2019) [41], STJML (2020) [42], GEF (2019) [43], DWDA (2021) [44], CDMA (2020) [45], ALML (2022) [46], TTLC (2021) [33], SGA-MDAP (2020) [47], NSO (2020) [48], FSUTL (2020) [49], PLC (2021) [50], GSI (2021) [51] and ICDAV (2022) [52]. In the experiments, VTL begins with learning a domain invariant and class discriminative latent feature space according to Equation (18).…”

Section: Resultsmentioning

confidence: 99%

Visual Transductive learning via Iterative Label Correction

Rezaie,

Ahmadvand,

Tahmoresnezhad

2023

Preprint

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) aims to transfer knowledge across domains when there is no labeled data available in the target domain. In this way, UDA methods attempt to utilize pseudo-labeled target samples to align distribution across the source and target domains. To mitigate the negative impact of inaccurate pseudo-labeling on knowledge transfer, we propose a novel UDA method known as visual transductive learning via iterative label correction (VTL) that benefits from a novel label correction paradigm. Specifically, we learn a domain invariant and class discriminative latent feature representation for samples of both source and target domains. Simultaneously, VTL attempts to locally align the information of samples by learning the geometric structure of samples. In the new shared feature space, the novel label correction paradigm is utilized to effectively maximize the reliability of pseudo labels by correcting inaccurate pseudo-labeled target samples, which significantly improves VTL classification performance. The experimental results on several object recognition tasks verified our proposed VTL superiority in comparison with other state-of-the-arts.

show abstract

Section: Resultsmentioning

confidence: 99%

Visual Transductive learning via Iterative Label Correction

Rezaie,

Ahmadvand,

Tahmoresnezhad

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Before being processed by SVM, the data used will be converted into a features vector using statistical calculations [31]. www.ijacsa.thesai.org The features selection method is one of the strategies to form a new features representation besides features mapping, features clustering, features encoding, features alignment, and features augmentation [32]. This strategy can preserve the local and important structure of the domain, besides, also reducing the distribution difference of the cross-domain.…”

Section: Machinementioning

confidence: 99%

“…In the proposed featuretransfer learning, MMD is used in conjunction with the kernel which will map the original value of the features space of each domain to a new features representation using a mapping function. Our proposed method uses a distance function as the mapping function, that is the Euclidean Distance and Reproducing Kernel Hilbert Space (RKHS) [13] [14] [15] [16] [18] [32]. The use of MMD and kernel makes it sufficient to calculate the similarity of the cross-domain using density estimation.…”

Section: Machinementioning

confidence: 99%

“…The third feature transformation adopts the gravity law, which is also similar to the general works of classification [41]. The use of distance has also been widely used in feature-transfer learning, such as for determining the weight proportion [8], determining the similarity between cross-domain [13] [14] [15], and the implementation of metric learning [32].…”

Section: B Inter-cluster Class Distancementioning

confidence: 99%

See 1 more Smart Citation

A Feature-based Transfer Learning to Improve the Image Classification with Support Vector Machine

Sevani¹,

Azizah²,

Jatmiko³

2023

IJACSA

View full text Add to dashboard Cite

In the big data era there are some issues regarding real-world classification problems. Some of the important challenges that still need to be overcome to produce an accurate classification model are the data imbalance, difficulties in labeling process, and differences on data distribution. Most classification problems are related to the differences in the data distribution and the lack of labels on some datasets while other datasets have abundant labels. To address the problem, this paper proposes a weighted-based feature-transfer learning (WbFTL) method to transfer knowledge between different but related domains, called cross-domain. The knowledge transfer is done through making a new feature representations in order to reduce the cross-domain's distribution differences while maintaining the local structure of the domain. To make the new feature representation we implement a feature selection and inter-cluster class distance. We propose two stages of the feature selection process to capture the knowledge of the feature and its relation to the label. The first stage uses a threshold to select the feature. The second stage uses ANOVA (Analysis of Variance) to select features that are significant to the label. To enhance the accuracy, the selected features are weighted before being used for the training process using SVM. The proposed WbFTL are compared to 1-NN and PCA as baseline 1 and baseline 2. Both baseline models represent the traditional machine learning and dimensionality reduction method, without implementing transfer learning. It is also compared with TCA, the first feature-transfer learning work on this same task, as baseline 3. The experiment results of 12 cross-domain tasks on Office and Caltech dataset show that the proposed WbFTL can increase the average accuracy by 15.25%, 6.83%, and 3.59% compared to baseline 1, baseline 2, and baseline 3, respectively.

show abstract