Large Margin Multi-Modal Multi-Task Feature Extraction for Image Classification

@article{Luo2016LargeMM,
  title={Large Margin Multi-Modal Multi-Task Feature Extraction for Image Classification},
  author={Yong Luo and Yonggang Wen and D. Tao and Jie Gui and Chao Xu},
  journal={IEEE Transactions on Image Processing},
  year={2016},
  volume={25},
  pages={414-427}
}
The features used in many image analysis-based applications are frequently of very high dimension. Feature extraction offers several advantages in high-dimensional cases, and many recent studies have used multi-task feature extraction approaches, which often outperform single-task feature extraction approaches. However, most of these methods are limited in that they only consider data represented by a single type of feature, even though features usually represent images from multiple modalities… Expand
Discriminative feature representation for image classification via multimodal multitask deep neural networks
TLDR
An end-to-end multimodal deep neural network (MDNN) framework to automate the feature selection and transformation procedures for image classification and inspired by Fisher’s theory of linear discriminant analysis, the proposed MDNN is improved by further proposing a multi-modal multitask deep Neural Network (M2DNN) model. Expand
A discriminative multi-class feature selection method via weighted l2, 1-norm and Extended Elastic Net
TLDR
Four types of weighting, which are based on correlation information between features and labels, are adopted to strengthen the discriminative performance of l 2,1 -norm joint sparsity. Expand
A Deep Multi-Modal CNN for Multi-Instance Multi-Label Image Classification
TLDR
A deep multi-modal CNN for multi-instance multi-label image classification, called MMCNN-MIML, which can automatically generate instance representations for MIML by exploiting the architecture of CNNs and incorporates the textual context of label groups to generate multi- modal instances, which are effective in discriminating visually similar objects belonging to different groups. Expand
Exploiting High-Order Information in Heterogeneous Multi-Task Feature Learning
TLDR
A tensor based heterogeneous MTFL framework to exploit high-order statistics which can only be discovered by simultaneously exploring all domains, and can obtain more reliable feature transformations compared with existing heterogeneous transfer learning approaches. Expand
An Unsupervised Feature Extraction Method based on Multi-granularity Convolution Denoising Autoencoder
  • Lijuan Cao, Qing Liu, Yun Yang
  • Computer Science
  • 2019 IEEE/ACIS 18th International Conference on Computer and Information Science (ICIS)
  • 2019
TLDR
The method proposed the concept of multi-granularity convolution kernel to solve the problem of complex image feature extraction and introduces denoising autoencoder (DAE) for image noise, which enables the approach to extract more robust features from noise images. Expand
Multi-View Exclusive Unsupervised Dimension Reduction for Video-Based Facial Expression Recognition
TLDR
This paper introduces exclusive group LASSO (EG-LASSO) to unsupervised dimension reduction (UDR) and extends EUDR to multi-view EUDR (MEUDR), where the structured sparsity is enforced at both intra- and interview levels. Expand
RGB-D Scene Classification via Multi-modal Feature Learning
TLDR
A new Convolutional Neural Networks-based local multi-modal feature learning framework (LM-CNN) for RGB-D scene classification that can effectively capture much of the local structure from the RGB- D scene images and automatically learn a fusion strategy for the object-level recognition step instead of simply training a classifier on top of features extracted from both modalities. Expand
Semi-supervised feature selection analysis with structured multi-view sparse regularization
TLDR
A structured multi-view sparse regularization is constructed and a novel semi-supervise feature selection framework is proposed, namely Structured Multi-view Hessian sparse Feature Selection (SMHFS). Expand
Low-rank matrix regression for image feature extraction and feature selection
TLDR
This work proposes a low-rank matrix regression model for feature extraction and feature selection, and develops an optimization algorithm based on the alternating direction method of multipliers method. Expand
Exploiting Combination Effect for Unsupervised Feature Selection by $\ell_{2,0}$ Norm
TLDR
This paper focuses on enhancing the unsupervised feature selection in another perspective, namely, making the selection exploit the combination effect of the features to improve the selection accuracy where the cluster structures are strongly related to a group of features. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 57 REFERENCES
Multiview Matrix Completion for Multilabel Image Classification
TLDR
Experimental evaluation on two real-world data sets demonstrate the effectiveness of MVMC for transductive (semisupervised) multilabel image classification, and show that MVMC can exploit complementary properties of different features and output-consistent labels for improved multilabe image classification. Expand
Manifold Regularized Multitask Learning for Semi-Supervised Multilabel Image Classification
TLDR
A manifold regularized multitask learning (MRMTL) algorithm that effectively controls the model complexity because different tasks limit one another's search volume, and the manifold regularization ensures that the functions in the shared hypothesis space are smooth along the data manifold. Expand
Multiview Vector-Valued Manifold Regularization for Multilabel Image Classification
TLDR
This work introduces multiview vector-valued manifold regularization (MV3MR), which exploits the complementary property of different features and discovers the intrinsic local geometry of the compact support shared by different features under the theme of manifoldRegularization. Expand
Multi-Class L2,1-Norm Support Vector Machine
TLDR
This paper is the first to give an efficient algorithm bridging the new problem with a previous solvable optimization problem to do multi-class feature selection, and it can obtain better or competitive performance compared with exiting state-of-art multi- class feature selection approaches. Expand
Group Sparse Multiview Patch Alignment Framework With View Consistency for Image Classification
TLDR
A group sparse multiview patch alignment framework (GSM-PAF) is developed that considers not only the complementary properties of different views, but also view consistency, which models the correlations between all possible combinations of any two kinds of view. Expand
From Transformation-Based Dimensionality Reduction to Feature Selection
TLDR
This paper introduces a general approach for converting transformation-based methods to feature selection methods through l1/l∞ regularization and illustrates how this approach can be utilized to convert linear discriminant analysis and the dimensionality reduction version of the Hilbert-Schmidt Independence Criterion to two new feature selection algorithms. Expand
Multi-View Clustering and Feature Learning via Structured Sparsity
TLDR
A novel multi-view learning model to integrate all features and learn the weight for every feature with respect to each cluster individually via new joint structured sparsity-inducing norms is proposed. Expand
Laplacian Score for Feature Selection
TLDR
This paper proposes a "filter" method for feature selection which is independent of any learning algorithm, based on the observation that, in many real world classification problems, data from the same class are often close to each other. Expand
Feature Extraction - Foundations and Applications
TLDR
This book discusses Feature Extraction for Classification of Proteomic Mass Spectra, Sequence Motifs: Highly Predictive Features of Protein Function, and Combining a Filter Method with SVMs. Expand
Multimodal semi-supervised learning for image classification
TLDR
This work considers a scenario where keywords are associated with the training images, e.g. as found on photo sharing websites, and learns a strong Multiple Kernel Learning (MKL) classifier using both the image content and keywords, and uses it to score unlabeled images. Expand
...
1
2
3
4
5
...