Kernel-Induced Label Propagation by Mapping for Semi-Supervised Classification

Zhang, Zhao; Jia, Lixin; Zhao, Mingbo; Liu, Guangcan; Wang, Meng; Yan, Shuicheng

doi:10.1109/tbdata.2018.2797977

Cited by 33 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, q = 1 → Q and we set Q = 3 as three different models are utilized to describe the set data. In order to aggregate such heterogeneous feature representations, three well-studied Riemannian kernel functions are then applied for high dimensional feature embeddings in the light of the proven success of kernel learning [43], [44], [45]. This process is implemented by mapping the original Riemannian manifoldvalued features into a Hilbert space, and then computing the dot product in it.…”

Section: B Multi-kernel Metric Learning For Heterogeneous Features Fmentioning

confidence: 99%

Multiple Riemannian Manifold-Valued Descriptors Based Image Set Classification With Multi-Kernel Metric Learning

Wang

Chen

et al. 2022

IEEE Trans. Big Data

View full text Add to dashboard Cite

The importance of wild video based image set recognition is becoming monotonically increasing due to the large amount of video resources obtained by diversified video collection approaches, like surveillance, drive recorders, smart phones, and internet. However, the contents of these collected videos are often complicated, and how to efficiently perform set modeling and feature extraction is a big challenge for set-based classification algorithms. In recent years, some proposed image set classification methods have made a considerable advance by modeling the original image set with covariance matrix, linear subspace, or Gaussian distribution. Moreover, the distinctive geometry spanned by them are Symmetric Positive Definite (SPD) manifold, Grassmann manifold, and Gaussian embedded Riemannian manifold, respectively. As a matter of fact, most of them just adopt a single geometric model to describe each given image set, which may lose some other useful information for classification. To tackle this problem, we propose a novel algorithm to model each image set from a multi-geometric perspective. Specifically, the covariance matrix, linear subspace, and Gaussian distribution are applied for set representation simultaneously. In order to fuse these multiple heterogeneous Riemannian manifoldvalued features, the well-equipped Riemannian kernel functions are first utilized to map them into high dimensional Hilbert spaces. Then, a multi-kernel metric learning framework is devised to embed the learned hybrid kernels into a lower dimensional common subspace for classification. We conduct experiments on four widely used datasets corresponding to four different classification tasks: video-based face recognition, set-based object categorization, video-based emotion recognition, and dynamic scene classification, to evaluate the classification performance of the proposed algorithm. Extensive experimental results justify its superiority over the state-of-the-art.

show abstract

Section: B Multi-kernel Metric Learning For Heterogeneous Features Fmentioning

confidence: 99%

Multiple Riemannian Manifold-Valued Descriptors Based Image Set Classification With Multi-Kernel Metric Learning

Wang

Chen

et al. 2022

IEEE Trans. Big Data

View full text Add to dashboard Cite

show abstract

“…Typical examples are label propagation (LP) and label spreading (LS). In LP and LS, kernel derivation by the mapping is performed to classify high-dimensional data [14]. The kernels used are the radial basis function (RBF) and k-nearest neighbor (KNN) algorithms, RBF is also called Gaussian kernels.…”

Section: Semi-supervised Learningmentioning

confidence: 99%

Quality Prediction and Yield Improvement in Process Manufacturing Based on Data Analytics

2020

View full text Add to dashboard Cite

Quality management is important for maximizing yield in continuous-flow manufacturing. However, it is more difficult to manage quality in continuous-flow manufacturing than in discrete manufacturing because partial defects can significantly affect the quality of an entire lot of final product. In this paper, a comprehensive framework that consists of three steps is proposed to predict defects and improve yield by using semi-supervised learning, time-series analysis, and classification model. In Step 1, semi-supervised learning using both labeled and unlabeled data is applied to generate quality values. In addition, feature values are predicted in time-series analysis in Step 2. Finally, in Step 3, we predict quality values based on the data obtained in Step 1 and Step 2 and calculate yield values with the use of the predicted value. Compared to a conventional production plan, the suggested plan increases yield by up to 8.7%. The production plan proposed in this study is expected to contribute to not only the continuous manufacturing process but the discrete manufacturing process. In addition, it can be used in early diagnosis of equipment failure.

show abstract

“…Based on the spectral graph theory, the connected points should be as close as possible in the latent common space. Following (Belkin and Niyogi 2003;Zhang et al 2018c), a reasonable criterion for choosing the transformations is to minimize the following objective function:…”

Section: Objective Functionmentioning

confidence: 99%

“…To use the label information, some supervised and semi-supervised methods are proposed to preserve the discrimination into the latent common space (Kan et al 2016;Zhang et al 2018b). Although supervised cross-modal methods have achieved promising performance by utilizing the label information, they entirely rely on the labeled data and have faced two problems: 1) it is time and cost-prohibitive to collect well-annotated data (Zhang et al 2018c;. Especially, considering the multimedia data, such a task is more undesirable since multiple modalities will remarkably increase the labeling workload; 2) a large number of unlabeled data are much easier to obtain, but they cannot be used by the supervised approaches.…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Multi-Modal Learning with Balanced Spectral Decomposition

Zhu

Peng

et al. 2020

AAAI

View full text Add to dashboard Cite

Cross-modal retrieval aims to retrieve the relevant samples across different modalities, of which the key problem is how to model the correlations among different modalities while narrowing the large heterogeneous gap. In this paper, we propose a Semi-supervised Multimodal Learning Network method (SMLN) which correlates different modalities by capturing the intrinsic structure and discriminative correlation of the multimedia data. To be specific, the labeled and unlabeled data are used to construct a similarity matrix which integrates the cross-modal correlation, discrimination, and intra-modal graph information existing in the multimedia data. What is more important is that we propose a novel optimization approach to optimize our loss within a neural network which involves a spectral decomposition problem derived from a ratio trace criterion. Our optimization enjoys two advantages given below. On the one hand, the proposed approach is not limited to our loss, which could be applied to any case that is a neural network with the ratio trace criterion. On the other hand, the proposed optimization is different from existing ones which alternatively maximize the minor eigenvalues, thus overemphasizing the minor eigenvalues and ignore the dominant ones. In contrast, our method will exactly balance all eigenvalues, thus being more competitive to existing methods. Thanks to our loss and optimization strategy, our method could well preserve the discriminative and instinct information into the common space and embrace the scalability in handling large-scale multimedia data. To verify the effectiveness of the proposed method, extensive experiments are carried out on three widely-used multimodal datasets comparing with 13 state-of-the-art approaches.

show abstract

Kernel-Induced Label Propagation by Mapping for Semi-Supervised Classification

Cited by 33 publications

References 41 publications

Multiple Riemannian Manifold-Valued Descriptors Based Image Set Classification With Multi-Kernel Metric Learning

Multiple Riemannian Manifold-Valued Descriptors Based Image Set Classification With Multi-Kernel Metric Learning

Quality Prediction and Yield Improvement in Process Manufacturing Based on Data Analytics

Semi-Supervised Multi-Modal Learning with Balanced Spectral Decomposition

Contact Info

Product

Resources

About